No abstract

No abstract

Curvelet transform is a promising tool for multi-resolution analysis on images. This paper explains a new approach for facial expression recognition based on curvelet features extracted using curvelet transform. Curvelet transform is applied on the database images and curvelet coefficients are obtained for selected scale for image analysis. Facial curvelet features are compressed using singular value decomposition (SVD) approach. Back propagation neural network (BPNN) and Adaptive Neuro-Fuzzy Inference System (ANFIS) are used as classifiers for classifying expressions into one of the seven categories like angry, disgust, fear, happy, neutral, sad and surprise. Experimentation is carried out on JAFFE database. The experimental results show that the novel approach is a better option for extracting feature values and classifying facial expressions.

No abstract

Abstract:In recent years, the popularity of portable devices for capturing images, video, text extraction, etc. become key problems to detect and recognize the text in images. Extraction of text information from images or scene involves binary, text detection, text localization, word segmentation, and enhancement and character recognition. But there are variations involved in text such as font style, font size, orientation, alignment, reflections and illumination effect, hybrid background and low contrast image make text extraction process too difficult and more challenging. A large number of approaches and methods have been proposed to address this problem but still none of them are perfect. This paper presents an effective approach where we come up with hybrid approach that combines SWT with OCR for text detection and recognition in an image and EBMT to translate detected text into Hindi language. General challenges for performing scene text detection are also discussed.