Behaviors, actions, pose, facial expressions, and speech are considered as channels that convey human emotions. Extensive research has been carried out to explore the relationships between these channels and emotions. The proposed method consists of a neural network-based solution combined with image processing and speech processing to classify the universal emotions: happy, anger, sad, and neutral. Speech processing includes extraction of spectral and temporal features like MFCC, energy, and then a set of values is given as input to the neural network. In image processing, Gabor filter texture features are used to extract a set of selected feature points. Mutual information is calculated and given as an input to the neural network for classification. The experimental results demonstrate the efficacy of audio-visual cues especially using few prominent features as overall accuracy of the combined approach is above 85%.

Visually impaired people face a lot of challenges while choosing clothes with complex patterns and colors. Rotation, scaling and variation in the light makes the cloth recognition problem a challenging task. An automatic cloth pattern recognition technique to classify the patterns into four classes namely plaid, striped, irregular and Patternless is developed using image processing, machine learning and deep learning concepts in this work. MATLAB is used as the simulation tool of choice. Color classification is done with the help of Hue Saturation Intensity (HSI) color model. To recognize clothing patterns, global and local features are extracted. Features extracted include Radon signatures and Grey Level Co-occurrence matrix. Pattern recognition has been done with the help of machine algorithms such as KNN, SVM, and deep learning networks such as AlexNet, GoogleNet, VGG-16 and VGG-19. To evaluate the effectiveness of the algorithms, CCNY Clothing Pattern data-set has been used. The maximum accuracy of 97.9% was obtained using the VGG-19 deep neural network.