Search

The elimination of blur due to camera shake and motion of the scene is been considered as a research topic in Image processing. An algorithm can be used to reduce the blur, which is capable of grouping many images, in that images less blurred image from each frame can be preferred through a weighted average in the Fourier Transform. The algorithm is simple to implement and very easy to define theoretically. To reduce the computation, complexity and to improve the quality of the image various algorithm has been proposed, which ultimately focuses on removal of blur. Irregular illumination can introduce severe distortions in the resulting images, decreasing the visibility of anatomical structures and consequently demoting the performance of the automated segmentation of these structures. There are several operators for example Prewitt, Sobel, Roberts, Canny edge detector are available, in which a mask is used as a template, that can be used to detect the edge pixels. There are Various methods and algorithms such as CNN, Morphological operations that are used to overcome this blur removal problem. As a result, it can be reduced and detected for several image issues. Among the operators Canny edge detector serves to be the best and for Blur correction Morphological operations has proven to be the classic one.

In our project, our intention is to create a voice and speech recognition system in smart phones that recognizes voice and captures the speech data in Tamil and stores and converts the captured speech as text in Tamil language itself. This can be used in voice dialing, sending SMS by saying out the message and the captured message is sent to the recipient in Tamil. There has not been much consideration for Tamil language to be used in voice and speech recognition in smart phones. For native users Tamil voice recognitions and speech would provide more flexibility in smart phone experience. Also people who have only been used to their native language Tamil, would feel easier to use the speech recognition system in their smart phones if provided in Tamil. There will be no more difficulty in usage of phones for local users and there is no need for any learning to use the smart phone. Automatic Speech Recognition (ASR) system have achieved a great success in many applications. Among them, Template Matching techniques like Dynamic Time Warping (DTW), Statistical Pattern Matching techniques such as Hidden Markov Model (HMM) and Gaussian Mixture Models (GMM), Machine Learning techniques such as Neural Networks (NN), Support Vector Machine (SVM), and Decision Trees (DT) are most popular. For this system, highest word recognition accuracy is achieved with HMM technique. It offered 100% accuracy during training process and approximately 98% for testing process.