No abstract

Binarization is a process of separation of pixel values of an input image into two pixel values like white as background and black as foreground. It is an important part in image processing and it is the first step in many document analysis and OCR processes. Most of the binarization techniques associate a certain intensity value called threshold which separate the pixel values of the concerned input grayscale image into two classes like background and foreground. Each and every pixel should be compared with the threshold and transformed to its respective class according to the threshold value. Thus threshold takes a major role in binarization. Hence determination of proper threshold value in binarization is a major factor of being a good binarised image and it can be approached in two categories like global thresholding and local thresholding techniques. In uniform contrast distribution of background and foreground documents, global thesholding is more suitable than that of local thresholding one. In degraded documents, where considerable background noise or variation in contrast and illumination exists, local technique is more suitable than that of global one. In this paper a local thresholding technique using local contrast and mean is described. Local adaptation is carried out with the local contrast and mean.

No abstract

Colon cancer is one of the highest cancer diagnosis mortality rates worldwide. However, relying on the expertise of pathologists is a demanding and time-consuming process for histopathological analysis. The automated diagnosis of colon cancer from biopsy examination played an important role for patients and prognosis. As conventional handcrafted feature extraction requires specialized experience to select realistic features, deep learning processes have been chosen as abstract high-level features may be extracted automatically. This paper presents the colon cancer detection system using transfer learning architectures to automatically extract high-level features from colon biopsy images for automated diagnosis of patients and prognosis. In this study, the image features are extracted from a pre-trained convolutional neural network (CNN) and used to train the Bayesian optimized Support Vector Machine classifier. Moreover, Alexnet, VGG-16, and Inception-V3 pre-trained neural networks were used to analyze the best network for colon cancer detection. Furthermore, the proposed framework is evaluated using four datasets: two are collected from Indian hospitals (with different magnifications 4X, 10X, 20X, and 40X) and the other two are public colon image datasets. Compared with the existing classifiers and methods using public datasets, the test results evaluated the Inception-V3 network with the accuracy range from 96.5% - 99% as best suited for the proposed framework.

No abstract