In the present work, we describe the study and performance of a robust text detection method in color and regular images. The system employs two important stages: Firstly the combination of wavelet transforms and gabor filter is applied to extract sharpened edges and textural features of a given input image. In the second stage, wavelet entropy is imposed to get an energy value of a resulted gabor image in order to find the high frequency texture elements of a processed one to determine the true text region of an image. Experiments are conducted on standard ICDAR database and with multi-lingual dataset. Experimental results show that the proposed method is able to detect text of different font size, complex background and contrast. Furthermore, the system performance surpasses the existing method in terms of detection accuracy.
: Textline segmentation in handwritten documents is of real challenge and interesting in the field of document image processing. In this paper, we propose a handwritten textline segmentation scheme based on the concept of linked list. The proposed method consists of three stages, namely, preprocessing, linked list and mathematical morphology. The concept of the linked list approach is used to build a textline sequence and mathematical morphology is used to obtain the line separator. We experimentally evaluated our proposed method on a document containing handwritten Kannada script. The results are compared with recent methods and show encouraging results.
The main objective of the proposed work is to develop an automated computer-aided detection (CAD) system to classify lung nodules using various classifiers from computed tomography (CT) images. One of the most important steps in lung nodule detection is the classification of nodule and non-nodule patterns in CT. The early detection of the condition helps lower the mortality rate. The developed CAD systems consist of segmentation, feature extraction, and classification. In this work, a filter method is used to segment the infected region. Later, we extracted features through and fed into classifiers such as Decision Stump (DS), Random Forest (RF), and Back Propagation Neural Network (BPNN). The experimentation was conducted on LIDC-IDRI dataset, and the results with BPNN outperformed those with DS and RF classifiers.