Search

Age recognition from faces has attracted potential interest due to its importance in several areas as well as minor-security and online shopping. However, it still has various challenges, especially in an unconstrained environment such as anti-aging treatments, illumination conditions, and filter effects. To deal with these problems, we choose to extract geometric features from face images. Thus, our proposed method consists firstly, of verifying if the acquired image contains a face. Then, the landmarks coordinates are calculated and the image is divided into 4 blocks. In each block, cross-distances are calculated and only max distances are considered to compute ratios. Finally, distances and ratios-max distances are fused to represent the age. In relation with the insufficient data issues and real time responses requirement in the Application Programming Interface (API), we highlight the relative role of using the handcrafted-based features compared to deep learning method for the proposed purpose. On the other hand, imbalanced data and intra-class variability present another famous challenge aiming to decrease the performance results. To overcome these issues, we proposed a multi-level classification strategy. Our developed approach is evaluated using FG-NET and Adience datasets, and the obtained results are effective compared to other recent existing works. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Jilin University (Science Edition) / Jilin Daxue Xuebao (Lixue Ban) is the property of Zhongguo Xue shu qi Kan (Guang Pan Ban) Dian zi Za zhi She and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Facial age recognition has been widely used in real-world applications. Most of current facial age recognition methods use deep learning to extract facial features to identify age. However, due to the high dimension features of faces, deep learning methods might extract a lot of redundant features, which is not beneficial for facial age recognition. To improve facial age recognition effectively, this paper proposed the deep manifold learning (DML), a combination of deep learning and manifold learning. In DML, deep learning was used to extract high-dimensional facial features, and manifold learning selected age-related features from these high-dimensional facial features for facial age recognition. Finally, we validated the DML on Multivariate Observations of Reactions and Physical Health (MORPH) and Face and Gesture Recognition Network (FG-NET) datasets. The results indicated that the mean absolute error (MAE) of MORPH is 1.60 and that of FG-NET is 2.48. Moreover, compared with the state of the art facial age recognition methods, the accuracy of DML has been greatly improved.

Hidden Markov models (HMMs) were developed and implemented to discriminate between each of the 2 ages, 11 call-types, and 51 speakers of birds using cross-validation on the recordings in the 3314 database for chick (19–25 days of age) and adult (60 days–7 years of age) vocalizations of Zebra Finches (Taeniopygia guttata). By applying both temporal [delta (velocity) and delta-delta (acceleration) coefficients] and spectral [Mel-Frequency Cepstral Coefficients (MFCCs)] features, the HMMs produced excellent performance with accuracies on the three tasks: (1) 96.68% (age recognition); (2) 94.62% (chicks) and 79.30% (adults) (call-type classification); and (3) 55.32% (12 speakers, chicks) and 16.78% (33 speakers, adults) to 100.00% (2 speakers, chicks), and 100.00% (3 speakers adults) (speaker identification). Based on the performances, the HMMs could be extended to other animals for automatic recognition, classification, and identification tasks. [ABSTRACT FROM AUTHOR]

To solve the problem that the available datasets for face age recognition were generally insufficient, and improve the accuracy of face age recognition with the same available dataset, the label distribution learning (LDL) strategy was introduced into the deep learning (DL) framework and named as DL-LDL. Convolutional neural networks were used to automatically extract facial features, and the improved label distribution learning was used to learn the fuzziness and ambiguity between the real age and the adjacent ages for enriching the age information and improving the recognition accuracy. The DL-LDL method was tested on two open datasets of MORPH and FG-NET. The results show that the DL-LDL method can improve the accuracy of age recognition. Compared with the most advanced facial age recognition method at present, the mean absolute errors of MORPH and FG-NET are reduced by 8.2% and 13.8%, respectively. [ABSTRACT FROM AUTHOR]

Human-Computer Interaction (HCI) in an intelligent way, which aims at creating scalable and flexible solutions. Big tech firms and businesses believe in the success of HCI as it allows them to profit from on-demand technology and infrastructure for information-centric applications without having to use public clouds. Because of its capacity to imitate human coding abilities, facial expression recognition and software-based facial expression identification systems are crucial. This paper proposes a system of recognizing the emotional condition of humans, given a facial expression, and conveys two methods of predicting the age and gender factors from human faces. This research also aims in understanding the influences posed by gender and age of humans on their facial expressions. The model can currently detect 7 emotions based on the facial data of a person - (Anger, Disgust, Happy, Fear, Sad, Surprise, and Neutral state). The proposed system is divided into three segments: a.) Gender Detection b.) Age Detection c.) Emotion Recognition. The initial model is created using 2 algorithms - KNN, and SVM. We have also utilized the architectures of some of the deep learning models such as CNN and VGG - 16 pre-trained models (Transfer Learning). The evaluation metrics show the model performance regarding the accuracy of the Recognition system. Future enhancements of this work can include the deployment of the DL and ML model onto an android or a wearable device such as a smartphone or a watch for a real-time use case. [ABSTRACT FROM AUTHOR]

In classification tasks, training labels are usually specified as one-hot targets which represent each class equally and exclusively. However, this labeling rule is not suitable in some situations. For the dependent classes, one-hot targets are not capable to represent the relation among them. The existing label smoothing methods just split the target response into neighboring classes, but it is only applied for ordinal classification, but not for the dependent but non-ordered classes. In this paper, we propose a novel labeling rule that decomposes the one-hot target into several bases to reflect relationships among classes while maintaining a balanced target space, which adopts channel encoding from communication systems, in particular, Bose–Chaudhuri–Hocquenghem (BCH) encoding. Besides, BCH encoder has an error-correcting mechanism that is expected to lift the accuracy. In theory, training with BCH targets ensures improved classification performance given the original accuracy is not less than 50%. To verify the proposed method on dependent classification, we conduct experiments with two facial tasks: age recognition and face anti-spoofing. The former is an ordinal classification task, and the latter is also regarded as a specific dependent classification problem due to the varying attack types being classified as one class finally and real for the other. Experimental results show that the proposed method improves accuracy by 6.33% on age recognition and reduces HTER by 3.63% for face anti-spoofing. In addition, as BCH targets divide the original response into a higher dimensional space, that is, the model is made to be heeded on learning the delicate sub-features. Hence, BCH targets also enhance model generalizability, thus guaranteeing improved performance on cross-domain evaluations. We further perform an assessment on the PACS dataset for evaluating domain generalizability. The results show that the domain generalizability is enhanced by increasing average accuracy by over 2% training with BCH targets.

According to several studies, children’s speech is more dynamic and inconsistent compared to an adult’s speech. This aspect can be considered in the task of recognizing the age of the person who speaks and of great importance in many applications, such as humancomputer interaction, security on Internet and education assistants. Those applications have a dependency on language and accent, due to the different sounds and styles that characterize the speakers. This paper presents the initial results on the identification of Costa Rican children’s speech, in a database created for this purpose, consisting of words pronounced by adults and children of several ages. For this first study we chose the most common vowel of the language, and extract a set of common acoustic features to determine its applicability in distinguishing between adults and children of an age range. The outcome results shows promising results in the classification using a single vowel, that improves according to the number of vowels used to extract the acoustic features. This means that an automatic system could be able to improve its capacity to identify age as more speech information is received and transcribed, but cannot be very accurate in short interactions.

Emotion recognition from facial images is considered as a challenging task due to the varying nature of facial expressions. The prior studies on emotion classification from facial images using deep learning models have focused on emotion recognition from facial images but face the issue of performance degradation due to poor selection of layers in the convolutional neural network model.To address this issue, we propose an efficient deep learning technique using a convolutional neural network model for classifying emotions from facial images and detecting age and gender from the facial expressions efficiently. Experimental results show that the proposed model outperformed baseline works by achieving an accuracy of 95.65% for emotion recognition, 98.5% for age recognition, and 99.14% for gender recognition. [ABSTRACT FROM AUTHOR]

In this article, we propose the Random Occlusion, a data augmentation method on facial images using simple image processing techniques for age and gender recognition. Previous methods achieved promising results on constrained datasets with strict environmental settings, but the results on unconstrained datasets are still far from perfect. This article proposed a data augmentation method by altering the training images that resemble real-life photos to improve the performance of the networks by providing more varieties to the training samples. The proposed method adopted three simple occlusion techniques, Blackout, Random Brightness, and Blur, and each simulates a different kind of challenge that would be encountered in real-world applications. We verify the effectiveness of the proposed method by implementing the augmentation method on two convolution neural networks (CNNs), the modified AdienceNet and VGG16 to perform age and gender classification. The proposed augmentation method improves the age accuracy results of the modified AdienceNet and VGG16 by 1.0% and 0.8%, respectively; and gender accuracy results of the AdienceNet and VGG16 by 1.5% and 1.2%, respectively. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Jilin University (Science Edition) / Jilin Daxue Xuebao (Lixue Ban) is the property of Zhongguo Xue shu qi Kan (Guang Pan Ban) Dian zi Za zhi She and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Being aware of the different social expectations linked to the principal lifespan stages (i.e., childhood, adulthood, old age) is critical to an individual's inclusion in the community and to developing appropriate social behaviours. However, little research exists on this topic in the field of intellectual and developmental disabilities. Sixty-nine adults with intellectual disability (ID) took part in the study. They completed a new task specifically developed to assess lifespan stages recognition among persons with ID. Participants' verbal and nonverbal reasoning skills were also assessed. The results of this study suggest that the performance of adults with ID in recognising different lifespan stages is related to specific cognitive abilities and to the type of material used to test this performance. Implications of these results and the possible use of the task in educational settings are discussed. [ABSTRACT FROM AUTHOR]

Facial age recognition has been widely used in real-world applications. Most of current facial age recognition methods use deep learning to extract facial features to identify age. However, due to the high dimension features of faces, deep learning methods might extract a lot of redundant features, which is not beneficial for facial age recognition. To improve facial age recognition effectively, this paper proposed the deep manifold learning (DML), a combination of deep learning and manifold learning. In DML, deep learning was used to extract high-dimensional facial features, and manifold learning selected age-related features from these high-dimensional facial features for facial age recognition. Finally, we validated the DML on Multivariate Observations of Reactions and Physical Health (MORPH) and Face and Gesture Recognition Network (FG-NET) datasets. The results indicated that the mean absolute error (MAE) of MORPH is 1.60 and that of FG-NET is 2.48. Moreover, compared with the state of the art facial age recognition methods, the accuracy of DML has been greatly improved.

A problem of age recognition from a human's face is developed with the popularization of convolutional neural networks. They make it possible to determine the specific features of faces, unseen by a human eye, and interpret them as age characteristics. Existing approaches to age recognition are analyzed. Data from existing sets for learning with subsequent correction for reducing the errors made in labels by acquisition algorithms are used. Neural networks are taught and tested using the resulting data. There is a problem with head rotation, whose solution is carried out using the images of faces rotated using the PRNet neural network. [ABSTRACT FROM AUTHOR]

Face analysis in images in the wild still pose a challenge for automatic age and gender recognition tasks, mainly due to their high variability in resolution, deformation, and occlusion. Although the performance has highly increased thanks to Convolutional Neural Networks (CNNs), it is still far from optimal when compared to other image recognition tasks, mainly because of the high sensitiveness of CNNs to facial variations. In this paper, inspired by biology and the recent success of attention mechanisms on visual question answering and fine-grained recognition, we propose a novel feedforward attention mechanism that is able to discover the most informative and reliable parts of a given face for improving age and gender classification. In particular, given a downsampled facial image, the proposed model is trained based on a novel end-to-end learning framework to extract the most discriminative patches from the original high-resolution image. Experimental validation on the standard Adience, Images of Groups, and MORPH II benchmarks show that including attention mechanisms enhances the performance of CNNs in terms of robustness and accuracy. [ABSTRACT FROM AUTHOR]

Mobile devices are nowadays ubiquitous. They are equipped with a variety of sensors, each designed for capturing specific signals which can be exploited to acquire discriminating user's traits, thus allowing to recognize, for instance, the authorized users. In this regard, we focus on capturing soft biometric traits from smartphones. Soft biometric information extracted from a human body (e.g., gender and age) is ancillary information proved to improve the performance of biometric authentication systems, and it has drawn a great deal of attention for its applications in healthcare, smart spaces and digital world as a whole. This paper presents an approach to gender and age-group recognition, namely TGSB , leveraging a transfer learning strategy applied to state-of-the-art Convolutional Neural Networks (CNNs) fed with image-based representations of touch gestures performed by users on mobile devices. We perform experiments considering, one at a time, touch gestures of the same kind, and combinations thereof, with intermediate and late fusion learning strategies. Experiments prove that TGSB is a promising approach, with up to 94% accuracy for the gender recognition and up to 99% for the age-group recognition. We highlight the most useful touch gesture for gender and age-group recognition, that is Scroll with 81% and 96% accuracy, respectively. We show that combining multiple touch gestures (intermediate fusion) with a joint latent subspace learning mechanism in CNNs improves the TGSB performance, up to 99% accuracy when considering a combination of two Scroll. Compared to previous works, TGSB exhibits much better performance in both gender and age-group recognition. [ABSTRACT FROM AUTHOR]

In this article, we present the first child emotional speech corpus in Russian, called “EmoChildRu”, collected from 3 to 7 years old children. The base corpus includes over 20 K recordings (approx. 30 h), collected from 120 children. Audio recordings are carried out in three controlled settings by creating different emotional states for children: playing with a standard set of toys; repetition of words from a toy-parrot in a game store setting; watching a cartoon and retelling of the story, respectively. This corpus is designed to study the reflection of the emotional state in the characteristics of voice and speech and for studies of the formation of emotional states in ontogenesis. A portion of the corpus is annotated for three emotional states (comfort, discomfort, neutral). Additional data include the results of the adult listeners’ analysis of child speech, questionnaires, as well as annotation for gender and age in months. We also provide several baselines, comparing human and machine estimation on this corpus for prediction of age, gender and comfort state. While in age estimation, the acoustics-based automatic systems show higher performance, they do not reach human perception levels in comfort state and gender classification. The comparative results indicate the importance and necessity of developing further linguistic models for discrimination. [ABSTRACT FROM AUTHOR]

Many snakes are able to use their chemosensory system to detect scent of conspecifics, which is important in many social contexts. Age discrimination based on chemical cues may be especially important to ensure access to sexually mature potential partners. In this study, we used 24 individual Boa constrictor snakes (12 adults mature and 12 non-mature individuals) that had been captured in different areas of Ecuador, and were maintained in captivity at the Vivarium of Quito. We used tongue-flick experiments to examine whether these snakes were able to discriminate between scents from mature and non-mature individuals. Results showed that B. constrictor snakes used chemical cues to recognize conspecifics and that the scent of individuals of different ages elicited chemosensory responses of different magnitudes. The scents from adult conspecifics elicited the quickest and highest chemosensory responses (i.e., short latency times and high tongue-flick rates), although we did not find differential responses to scent of males and females. The magnitude of the responses was lower to scent of sub adult individuals, and then even lower to scent of juvenile snakes, but in all cases the scent of snakes was discriminated from a blank control. We discuss the potential chemical mechanisms that may allow age recognition and its implications for social and sexual behavior of this snake species.Muchas serpientes son capaces de usar su sistema quimiosensorial para detectar el olor de individuos coespecíficos, lo que es importante en muchos contextos sociales. La discriminación de la edad basada en señales químicas puede ser especialmente importante para asegurar el acceso a parejas potenciales que sean sexualmente maduras. En este estudio, usamos 24 individuos de una especie de boa (Boa constrictor) (12 individuos adultos y 12 inmaduros) que habían sido capturados en diferentes partes de Ecuador y eran mantenidos en cautividad el Vivarium de Quito. Usamos experimentos de protusiones linguales para examinar si esta serpiente es capaz de discriminar entre el olor de individuos maduros y no maduros. Los resultados mostraron que B. constrictor usa señales químicas para reconocer co-específicos y que el olor de individuos de distinta edad provoca respuestas quimiosensoriales de diferente magnitud. El olor de individuos adultos provocó las respuestas más rápidas y elevadas (esto es, tiempos de latencia más cortos y tasas más altas de protusiones linguales), aunque no encontramos diferencias en las respuestas a olores de machos y hembras. La magnitud de las respuestas fue más baja a olores de sub adultos, e incluso más baja a olor de juveniles, pero en todos los casos el olor de una serpiente era discriminado de un control no oloroso. Discutimos los posibles mecanismos químicos que pueden permitir esta discriminación de la edad y sus implicaciones para el comportamiento social y sexual de esta serpiente.

Age estimation can be effectively used in security, human–computer interaction, entertainment, and audio-visual fields. However, current face-based age recognition algorithms are not highly accurate due to factors, such as face makeup and plastic surgery. Among the various feature points of a human face, the eyes are the most difficult part to be modified. And with the changes of age, the lens, cornea, and vitreous of eyes will also change accordingly. Therefore, we believe that paying attention to the local feature of the eye can improve the accuracy of age estimation to a certain extent. The multilevel feature convolutional neural network (MLFCNN) is proposed, which values eyes features and combines them with face features to jointly estimate human age. MLFCNN performs two rounds of estimation based on extracted features. First, the age range of the sample is estimated as the age group, and then on this basis, the fine age of the sample is further estimated. Field tests show that the mean absolute error of MLFCNN is 2.87, which is lower than other network models tested. When the MLFCNN estimated age did not differ more than 4 years from the actual age of the sample, the network predictions were considered correct (i.e., the tolerable age error was 4). The age estimation accuracy of MLFCNN under this condition was 91.14%. And 98.32% accuracy can be reached when the tolerable age error is 6. Ablation experiments verify that the fusion of ocular features and facial features can improve the performance of the age estimation network. In addition, it can still maintain a good performance under small training dataset. [ABSTRACT FROM AUTHOR]

Abstract: The paper presents a novel automatic speaker age and gender identification approach which combines seven different methods at both acoustic and prosodic levels to improve the baseline performance. The three baseline subsystems are (1) Gaussian mixture model (GMM) based on mel-frequency cepstral coefficient (MFCC) features, (2) Support vector machine (SVM) based on GMM mean supervectors and (3) SVM based on 450-dimensional utterance level features including acoustic, prosodic and voice quality information. In addition, we propose four subsystems: (1) SVM based on UBM weight posterior probability supervectors using the Bhattacharyya probability product kernel, (2) Sparse representation based on UBM weight posterior probability supervectors, (3) SVM based on GMM maximum likelihood linear regression (MLLR) matrix supervectors and (4) SVM based on the polynomial expansion coefficients of the syllable level prosodic feature contours in voiced speech segments. Contours of pitch, time domain energy, frequency domain harmonic structure energy and formant for each syllable (segmented using energy information in the voiced speech segment) are considered for analysis in subsystem (4). The proposed four subsystems have been demonstrated to be effective and able to achieve competitive results in classifying different age and gender groups. To further improve the overall classification performance, weighted summation based fusion of these seven subsystems at the score level is demonstrated. Experiment results are reported on the development and test set of the 2010 Interspeech Paralinguistic Challenge aGender database. Compared to the SVM baseline system (3), which is the baseline system suggested by the challenge committee, the proposed fusion system achieves 5.6% absolute improvement in unweighted accuracy for the age task and 4.2% for the gender task on the development set. On the final test set, we obtain 3.1% and 3.8% absolute improvement, respectively. [Copyright &y& Elsevier]

Many snakes are able to use their chemosensory system to detect scent of conspecifics, which is important in many social contexts. Age discrimination based on chemical cues may be especially important to ensure access to sexually mature potential partners. In this study, we used 24 individual Boa constrictor snakes (12 adults mature and 12 non-mature individuals) that had been captured in different areas of Ecuador, and were maintained in captivity at the Vivarium of Quito. We used tongue-flick experiments to examine whether these snakes were able to discriminate between scents from mature and non-mature individuals. Results showed that B. constrictor snakes used chemical cues to recognize conspecifics and that the scent of individuals of different ages elicited chemosensory responses of different magnitudes. The scents from adult conspecifics elicited the quickest and highest chemosensory responses (i.e., short latency times and high tongue-flick rates), although we did not find differential responses to scent of males and females. The magnitude of the responses was lower to scent of sub adult individuals, and then even lower to scent of juvenile snakes, but in all cases the scent of snakes was discriminated from a blank control. We discuss the potential chemical mechanisms that may allow age recognition and its implications for social and sexual behavior of this snake species. [ABSTRACT FROM AUTHOR]

Abstract: Present translation systems play back their results with specific speed and volume regardless of the type of user. In this paper, we describe a personalized translation listening system by identifying user information. User groups are classified by age group after inputting speech. This suggested translation system gives the translated result back to the user, speaking at an emphasized speech based on the user''s age. The personalized translation listening system performs age recognition, speech recognition, language recognition, Google machine translation, and TTS web services. We showed the comparison of normal speech and emphasized speech by realizing a user-oriented translation system in a mobile device. A Mean Opinion Score was used for the experiment. Average score of the Mean Opinion Score experiment was 3.21. [Copyright &y& Elsevier]

Parental care is an important factor influencing offspring survival and adult reproductive success in many vertebrates. Parent-offspring recognition ensures care is only directed to filial young, avoiding the costs of misallocated resource transfer. It is essential in colonial mammal species, such as otariids (fur seals and sea lions), in which repeated mother-offspring separations increase the risk of misdirecting maternal effort. Identification of otariid pups by mothers is known to be multi-modal, yet the role of visual cues in this process remains uncertain. We used three-dimensional visual models to investigate the importance of visual cues in maternal recognition of pups in Australian sea lions ( Neophoca cinerea ). We showed that the colour pattern of pup pelage in the absence of any other sensory cues served to attract the attention of females and prompt investigation. Furthermore, females were capable of accurately distinguishing between models imitating the age-class of their own pup and those resembling older or younger age-classes. Our results suggest that visual cues facilitate age-class discrimination of pups by females and so are likely to play an important role in mother-pup reunions and recognition in otariid species., (© 2017 The Author(s).)