Search

We propose an image super-resolution method (SR) using a deeply-recursive convolutional network (DRCN). Single-image super-resolution reconstruction technology is to reconstruct fuzzy low-resolution images into clearer high-resolution images. It is a research hotspot in the field of computer vision and image processing. In recent years, the attention mechanism has been successfully applied in image super-resolution reconstruction. However, the existing methods use the channel attention mechanism and the spatial attention mechanism separately, or simply superimpose them, which cannot effectively unify the adjustment effects of both, and the performance is limited. This paper proposes a method that can merge channel attention and spatial attention into pixel attention, which achieves more precise adjustment of feature map information. The pixel attention convolutional neural network method built on this basis can improve the quality of image texture detail reconstruction. We have been tested on five widely used standard datasets, the experimental results show that the method is superior to most current representative reconstruction methods, especially in terms of high-definition picture texture restoration. [ABSTRACT FROM AUTHOR]

In the world, several sign languages (SL) are used, and BSL (Baby Sign Language) is the process of communication between the parents and baby using gestures. Communication by gestures is a non-verbal process that utilizes motion to pass on realities, expressions and feelings to people. SL is the communication mode in which the information is conveyed via movement of body parts like cheeks, eyebrows and head. Even though many research works based on SL are available, research in BSL remains a challenge. Hence, this paper presents an optimization-based automated recognition of the deep BSL system, which determines the gesture signalled by the kids. Initially, the image frames are extracted from the videos and data augmentation processes are performed. After pre-processing, the features are extracted from the frames using the Enhanced Convolution Neural Network (ECNN). The optimal characteristics are then selected by a new Life Choice Based Optimizer (LCBO). Finally, the classification is carried out by the Deep Long Short-Term Memory (DLSTM) scheme. The implementation is performed on the Python platform, and the performances are evaluated using several performance metrics such as accuracy, precision, kappa, f1-score and recall. The performance of the proposed approach (ECNN-DLSTM) is compared with several deep and machine learning approaches and obtains an accuracy of 99% and a kappa of 96%. [ABSTRACT FROM AUTHOR]

Image classification becomes a popular research area in computer vision due to the increasing development of image indexing and retrieval tasks. This paper proposes a Flower Henry Gas Solubility Optimization-based Deep Convolution Neural Network (FHGSO-based Deep CNN) for image classification. Initially, the input image is pre-processed through the median filter. Then, the segmentation is performed using the Improved Invasive Weed Flower Pollination Optimization (IIWFPO)-based SegNet. IIWFPO is the integration of the Improved invasive weed optimization (IWO) algorithm and Flower Pollination Algorithm (FPA). Finally, image classification is performed using FHGSO-based Deep CNN. The FHGSO algorithm is developed by integrating the FPA and Henry Gas Solubility Optimization (HGSO) algorithm. The performance of the proposed method is analyzed using the Stanford background dataset and compared with the other image classification methods. The proposed model obtained the value of 0.938, 0.955, and 0.907 for testing accuracy, sensitivity, and specificity, respectively. [ABSTRACT FROM AUTHOR]

Convolutional Neural Networks (CNN) are being widely practised in computer vision applications, where pooling indicates as an integral part. Pooling significantly reduces the training time and computational cost of any network. The pooling operations generally being used are max, average, or stochastic. The performance of the CNN architecture can be increased by using more than one pooling operations. Herein, a novel mixed fuzzy pooling is proposed for image classification in the CNN architecture. In the proposed mixed fuzzy pooling, max pooling and fuzzy pooling are combined together to boost the classification accuracy. The proposed mixed fuzzy pooling is designed as a function of max pooling, fuzzy pooling, and α parameter where the learning of the proposed pooling function takes place with the value of α. In fuzzy pooling, Type-2 fuzzy logic is used to get the convolved dominant features. This is obtained by the estimation of a threshold for image region to be pooled. Thereafter, Type-1 fuzzy logic is used to get the pooling output by a weighted average of convolved dominant features. The performance of various pooling strategies on MNIST dataset for handwritten digits classification and CIFAR-10 dataset for RGB images classification have been compared and analysed. The experimental results show better image classification accuracy for the proposed mixed fuzzy pooling than conventional pooling operations. [ABSTRACT FROM AUTHOR]

Automating the fabric inspection process has been attempted by several researchers in the past. However, the numerous variants of fabric, such as their construction, texture, print, and colour along with the huge gamut of fabric defects which exist, complicate the process of automating defect detection, thus making it an open challenge for researchers to come up with a one-stop, full proof robust automation solution. In the present study, an attempt has been made to detect, classify, and locate four different types of fabric defects on solid wovens, hole, knot, slub and stain, which contributes 86% of total fabric defects; using the convolutional neural network (CNN) through transfer learning on the MATLAB® platform and computer vision technology. The image dataset in this study consists of 5000 images, which is one of the largest reported till date and collected from real working environments of different apparel manufacturing units. The methodology involves four different approaches—detection approach, hierarchical approach, classification approach, and object location approach. For algorithm development, transfer learning has been adopted in which the pre-trained deep learning architectures are fine-tuned as per specific case requirement. In this study, 4 state-of-the-art deep learning models were selected as follows: VGG16, VGG19, ResNet101 and DarkNet53. This study not only focuses on defect detection and classification but also on defect location which is detailed in its fourth approach. For object location, YOLOv3 architecture was used. The defect detection, classification and location identification systems attained an accuracy of 95%, 88% and 97%, respectively. The developed model was tested on different platforms viz. Internet-based webcam and MATLAB® cloud. Detailed investigation towards challenges faced by models specific to class of defect was carried out and reported thus adding insights for probable modification required in the model. The study proposes an industry ready system for real-time implementation. [ABSTRACT FROM AUTHOR]

Recently, the progress on image understanding and AIC (Automatic Image Captioning) has attracted lots of researchers to make use of AI (Artificial Intelligence) models to assist the blind people. AIC integrates the principle of both computer vision and NLP (Natural Language Processing) to generate automatic language descriptions in relation to the image observed. This work presents a new assistive technology based on deep learning which helps the blind people to distinguish the food items in online grocery shopping. The proposed AIC model involves the following steps such as Data Collection, Non-captioned image selection, Extraction of appearance, texture features and Generation of automatic image captions. Initially, the data is collected from two public sources and the selection of non-captioned images are done using the ARO (Adaptive Rain Optimization). Next, the appearance feature is extracted using SDM (Spatial Derivative and Multi-scale) approach and WPLBP (Weighted Patch Local Binary Pattern) is used in the extraction of texture features. Finally, the captions are automatically generated using ECANN (Extended Convolutional Atom Neural Network). ECANN model combines the CNN (Convolutional Neural Network) and LSTM (Long Short-Term Memory) architectures to perform the caption reusable system to select the most accurate caption. The loss in the ECANN architecture is minimized using AAS (Adaptive Atom Search) Optimization algorithm. The implementation tool used is PYTHON and the dataset used for the analysis are Grocery datasets (Freiburg Groceries and Grocery Store Dataset). The proposed ECANN model acquired accuracy (99.46%) on Grocery Store Dataset and (99.32%) accuracy on Freiburg Groceries dataset. Thus, the performance of the proposed ECANN model is compared with other existing models to verify the supremacy of the proposed work over the other existing works. [ABSTRACT FROM AUTHOR]

Hyperspectral images (HIs) are used in diverse disciplines, such as resource handling, land cover analysis, food science, anomaly detection, and precision agriculture. Researchers have been working on a number of visual processing and machine intelligence algorithms to handle this type of data as efficiently as feasible. Deep learning approaches have advanced significantly in the field of machine vision, which is also having a big impact on the analysis of hyperspectral data. To increase its discriminative potential for HI classification, this work suggests a powerful 3D-CNNs (Convolutional Neural Networks) architecture, where the shallow features extracted using 1D-EWT (Empirical Wavelet Transform) are served as input, and the ultimate output of the CNN are projected class-related outcomes. The framework is known as PEC, where P stands for PCA, E for 1D-EWT, and C for 3D-CNN model. Prior to features extraction, the HI undergoes spectral dimension reduction via Principal Component Anaalysis (PCA). To forecast segmentation for a volumetric area of a 3D HI sample, 3D CNNs use 3D convolutional kernels. The usage of more parameters by these CNNs means that the ability to employ interslice context that can boost performance. The CNN model's parameters are optimised using a limited training set. The newly proposed PEC framework achieves a considerable overall accuracy of 99.58% and 99.94% (percentage increase of 0.08% and 0.54%) and Kappa score of 99.51% and 99.92 (percentage increase of 1.5% and 0.8%) compared to similar approaches for two real-world data sets IP and PU respectively with 30% training samples. [ABSTRACT FROM AUTHOR]

There are many types of haricot beans, the nutrient consumed all over the world. Each type differs in terms of features such as taste, size, economic value, etc. But even if they are different types, bean grains are frequently confused with each other. For these reasons, it is important to separate the bean grains of different species. For this purpose, a haricot bean dataset consisting of 33,064 images of 14 different bean types was created. By using these images, 3 different pre-trained Convolutional Neural Networks (CNN) were trained via the transfer learning method. Within the scope of the study, InceptionV3, VGG16, and VGG19 CNN models were used. These models were utilized for both end-to-end classification and extraction of image features. Firstly, the images were classified via Inception V3, VGG16, and VGG19 models. As a result of this classification, 84.48%, 80.63%, and 81.03% classification success were obtained from InceptionV3, VGG16, and VGG19 models, respectively. Secondly, the image features of these 3 models were taken from the layer just before the classification layer. Then, these features were given as input to the Support Vector Machine (SVM) and Logistic Regression (LR) models. Images were classified using six different models, InceptionV3 + SVM, VGG16 + SVM, VGG1 + SVM and InceptionV3 + LR, VGG16 + LR, VGG1 + LR. Classification successes obtained from InceptionV3 + SVM, VGG16 + SVM, and VGG19 + SVM were 79.60%, 81.97%, 80.64%, respectively. And, the classification successes obtained from InceptionV3 + LR, VGG16 + LR, and VGG19 + LR were 82.35%, 83.71%, and 83.54%, respectively. The InceptionV3, among all models, was determined to be the best classification model with a classification success of 84.48%. On the other hand, the model with the lowest classification success was determined to be the InceptionV3 + SVM. Detailed analysis of the created models was also carried out with precision, recall, and F-1 score metrics. It is thought that the proposed models can be used to distinguish haricot bean types in a quick and accurate way. Furthermore, the proposed computer vision methods can be combined with robotic systems and used to the distinction of bean types. By means of image processing, varieties can be determined on conveyor belts, and dry bean varieties can be purified with delta robots. [ABSTRACT FROM AUTHOR]

Facial expressions are essential in community based interactions and in the analysis of emotions behaviour. The automatic identification of face is a motivating topic for the researchers because of its numerous applications like health care, video conferencing, cognitive science etc. In the computer vision with the facial images, the automatic detection of facial expression is a very challenging issue to be resolved. An innovative methodology is introduced in the presented work for the recognition of facial expressions. The presented methodology is described in subsequent stages. At first, input image is taken from the facial expression database and pre-processed with high frequency emphasis (HFE) filtering and modified histogram equalization (MHE). After the process of image enhancement, Viola Jones (VJ) framework is utilized to detect the face in the images and also the face region is cropped by finding the face coordinates. Afterwards, different effective features such as shape information is extracted from enhanced histogram of gradient (EHOG feature), intensity variation is extracted with mean, standard deviation and skewness, facial movement variation is extracted with facial action coding (FAC),texture is extracted using weighted patch based local binary pattern (WLBP) and spatial information is extracted byentropy based Spatial feature. Subsequently, dimensionality of the features are reduced by attaining the most relevant features using Residual Network (ResNet). Finally, extended wavelet deep convolutional neural network (EWDCNN) classifier uses the extracted features and accurately detects the face expressions as sad, happy, anger, fear disgust, surprise and neutral classes. The implementation platform used in the work is PYTHON. The presented technique is tested with the three datasets such as JAFFE, CK+ and Oulu-CASIA. [ABSTRACT FROM AUTHOR]

As the basis of mid-level and high-level vision tasks, edge detection has great significance in the field of computer vision. Edge detection methods based on deep learning usually adopt the structure of the encoding-decoding network, among which the deep convolutional neural network is generally adopted in the encoding network, and the decoding network is designed by researchers. In the design of the encoding-decoding network, researchers pay more attention to the design of the decoding network and ignore the influence of the encoding network, which makes the existing edge detection methods have the problems of weak feature extraction ability and insufficient edge information extraction. To improve the existing methods, this work combines the information transmission mechanism of the retina/lateral geniculate nucleus with an edge detection network based on convolutional neural network and proposes a bionic feature enhancement network. It consists of a pre-enhanced network, an encoding network, and a decoding network. By simulating the information transfer mechanism of the retina/lateral geniculate nucleus, we designed the pre-enhanced network to enhance the ability of the encoding network to extract details and local features. Based on the hierarchical structure of the visual pathway and the integrated feature function of the inferior temporal (IT) cortex, we designed a novel feature fusion network as a decoding network. In a feature fusion network, a down-sampling enhancement module is introduced to boost the feature integration ability of the decoding network. Experimental results demonstrate that we achieve state-of-the-art performance on several available datasets. [ABSTRACT FROM AUTHOR]

Unsupervised machine learning offers significant opportunities for extracting knowledge from unlabeled datasets and for achieving maximum machine learning performance. This paper demonstrates how to construct, use, and evaluate a high-performance unsupervised machine learning system for classifying images in a popular microstructural dataset. The Northeastern University Steel Surface Defects Database includes micrographs of six different defects observed on hot-rolled steel in a format that is convenient for training and evaluating models for image classification. We use the VGG16 convolutional neural network pre-trained on the ImageNet dataset of natural images to extract feature representations for each micrograph. After applying principal component analysis to extract signal from the feature descriptors, we use k-means clustering to classify the images without needing labeled training data. The approach achieves 99.4% ± 0.16% accuracy, and the resulting model can be used to classify new images without retraining. This approach demonstrates an improvement in both performance and utility compared to a previous study. A sensitivity analysis is conducted to better understand the influence of each step on the classification performance. The results provide insight toward applying unsupervised machine learning techniques to problems of interest in materials science. [ABSTRACT FROM AUTHOR]

The risk of fires is ever increasing along with the boom of urban buildings. The current methods of detecting fire with the use of smoke sensors with large areas, however poses an issue. The introduction of video surveillance systems has given a great opportunity for identifying smoke and flame from faraway locations and tackles this risk. Processing this huge amount of data is a problem with using these video and image data. In recent times, a number of methods have been proposed to deal with this challenge and identify fire and smoke. Image processing algorithms for detecting flame and smoke, motion-based estimation of smoke, etc are some of the methods that are proposed earlier. Recently, there has been an array of methods proposed using Deep Learning, Convolutional Neural Networks (CNNs) to automatically detect and predict flame and smoke in videos and images. In this paper, we present a complete survey and analysis of these machine vision based fire/smoke detection methods and their performance. Firstly, we introduce the fundamentals of image processing methods, CNNs and their application prospect in video smoke and fire detection. Next, the existing datasets and summary of the recent methodologies used in this field are discussed. Finally, the challenges and suggested improvements to further the development of the application of CNNs in this field are discussed. CNNs are shown to have a great potential for smoke and fire detection and better development can help prepare a robust system that would greatly save human lives and monetary wealth from getting destroyed from fires. Finally, research guidelines are presented to fellow researchers regarding data augmentation, fire and smoke detection models which need to be investigated in the future to make progress in this crucial area of research. [ABSTRACT FROM AUTHOR]