Search

Emotions are strongly associated with individuals’ mood and personality. In the field of Human Computer Interaction, human face plays a very vital role. According to studies made by researchers’ majority of the information conveyed through facial expressions than verbal communication. In day-to-day life, human expresses different types of feelings such as Happiness, Anger, Sadness, Fear, Disgust and Surprise which is considered as “Universal Emotions”. It has always been difficult for computers to recognize human emotions. Thus, a substantial effort was made by the researchers to build the Facial Emotion Recognition system and which was considered as the best tool for recognizing emotions through facial expressions. In this paper, a detailed study on different methods that can be used in facial emotion recognition is done. For this study, the literature is collected from various reputable research published. This survey paper is based on the current approaches to face detection and feature extraction techniques for FER and also presented the real-time applications [ABSTRACT FROM AUTHOR]

Recent technological developments have enabled computers to identify and categorize facial expressions to determine a person's emotional state in an image or a video. This process, called "Facial Expression Recognition (FER)", has become one of the most popular research areas in computer vision. In recent times, deep FER systems have primarily concentrated on addressing two significant challenges: the problem of overfitting due to limited training data availability, and the presence of expression-unrelated variations, including illumination, head pose, image resolution, and identity bias. In this paper, a comprehensive survey is provided on deep FER, encompassing algorithms and datasets that offer insights into these intrinsic problems. Initially, this paper presents a detailed timeline showcasing the evolution of methods and datasets in deep facial expression recognition (FER). This timeline illustrates the progression and development of the techniques and data resources used in FER. Then, a comprehensive review of FER methods is introduced, including the basic principles of FER (components such as preprocessing, feature extraction and classification, and methods, etc.) from the pro-deep learning era (traditional methods using handcrafted features, i.e., SVM and HOG, etc.) to the deep learning era. Moreover, a brief introduction is provided related to the benchmark datasets (there are two categories: controlled environments (lab) and uncontrolled environments (in the wild)) used to evaluate different FER methods and a comparison of different FER models. Existing deep neural networks and related training strategies designed for FER, based on static images and dynamic image sequences, are discussed. The remaining challenges and corresponding opportunities in FER and the future directions for designing robust deep FER systems are also pinpointed. [ABSTRACT FROM AUTHOR]

Deep learning-based approaches are applied successfully in many fields such as deepFake identification, big data analysis, voice recognition, and image recognition. Deepfake is the combination of deep learning in fake creation, which states creating a fake image or video with the help of artificial intelligence for political abuse, spreading false information, and pornography. The artificial intelligence technique has a wide demand, increasing the problems related to privacy, security, and ethics. This paper has analyzed the features related to the computer vision of digital content to determine its integrity. This method has checked the computer vision features of the image frames using the fuzzy clustering feature extraction method. By the proposed deep belief network with loss handling, the manipulation of video/image is found by means of a pairwise learning approach. This proposed approach has improved the accuracy of the detection rate by 98% on various datasets. [ABSTRACT FROM AUTHOR]

The video inpainting process helps in several video editing and restoration processes like unwanted object removal, scratch or damage rebuilding, and retargeting. It intends to fill spatio-temporal holes with reasonable content in the video. Inspite of the recent advancements of deep learning for image inpainting, it is challenging to outspread the techniques into the videos owing to the extra time dimensions. In this view, this paper presents an efficient video inpainting approach using beetle antenna search with deep belief network (VIA-BASDBN). The proposed VIA-BASDBN technique initially converts the videos into a set of frames and they are again split into a region of 5*5 blocks. In addition, the VIABASDBN technique involves the design of optimal DBN model, which receives input features from Local Binary Patterns (LBP) to categorize the blocks into smooth or structured regions. Furthermore, the weight vectors of the DBN model are optimally chosen by the use of BAS technique. Finally, the inpainting of the smooth and structured regions takes place using the mean and patch matching approaches respectively. The patch matching process depends upon the minimal Euclidean distance among the extracted SIFT features of the actual and references patches. In order to examine the effective outcome of the VIA-BASDBN technique, a series of simulations take place and the results denoted the promising performance. [ABSTRACT FROM AUTHOR]