No abstract

Character recognition has been an active area of research and, due to its diverse applicable environment, it continues to be a challenging research topic. The data entry form is a convenient and successful tool for collection of information by filling the sheets with handwritten characters. For many purposes, such as documenting and archiving, extracting the handwritten characters is important. One of the most important fields in these forms is the data-filled boxes. The extraction process is important in processes of handwritten recognition techniques. Feature extraction plays an important role in different classification-based problems, such as face recognition, signature verification, optical character recognition (OCR), etc. The performance of OCR highly depends on the proper selection and extraction of a feature set. Different feature extraction methods are designed for different representations of the characters. The holistic approach is focused on feature extraction of the entire image and recognition using a neural network. This work proposes a subspace approach that regularizes and extracts Eigen features from handwritten numerals. Extracted Eigen features are recognized using a neural network. The proposed algorithm has been successfully implemented and has the added advantage of obtaining the extraction and recognition result at the same time.

Most of the patient diagnosis revolves around in identifying abnormalities in their respective medical images. These images are of various types, likely Ultrasound, CT scan, MRI and microscopic images like bio-chemical slides, micro-biological slides & pathological slides. Few abnormalities are fractures, bad cells in blood, tumors, fungal identification etc. Finding the abnormal portions in these images needs expertise by the physician; this apt identification promotes and guarantees healthy medication by the physician or surgeon to patient. In medical microscopic images normal portions and abnormal portions are mixed together. None of the abnormal portions are related to abnormal and normal portions of image i.e. deviations are scattered among normal portions of image. These deviations are not present in some portions for specific area in the images. None of these deviations are overlapped nor can be grouped together into a single portion physically in the image. Deviations are isolated along with normal portions of images. Identifying such deviations is vital. In previous methods these deviations are identified used BFS and Shortest Path Algorithm. This paper focuses on identifying deviations using parallel computing applied over fragmented portions of blood images using divide and conquer.