Support Vector Machines (SVM) is a machine learning method used for classifying the system. It analyses and identifies the categories using the trained data. It is widely used in medical field for diagnosing the disease. The proposed method consists of four phases. They are lung extraction, segmentation of lung region, feature extraction and finally classification of normal, benign and malignancy in the lung. Threat pixel identification with region growing method is used for segmentation of focal areas in the lung. For feature extraction gray level co-occurrence Matrix (GLCM) is been used. Extracted features are classified using different kernels of Support Vector Machine (SVM). The experimentation is performed with the help of real time computer tomography images.

In this paper, a attempt has been made to summarize some of the information about CAD and CADx for the purpose of early detection and diagnosis of lung cancer. Computer Aided Detection (CADe) and Computer Aided Diagnosis (CADx), are procedures in medical information that assist doctors in the interpretation of medical images. Imaging techniques in X-ray, MRI, and Ultrasound diagnostics yield a great deal of information, which the radiologist has to analyze and evaluate comprehensively in a short time. Thus, the use of digital computers to assist practitioners and physicians in diagnosing diseases and to offer a rapid access to medical information gained importance. CAD systems help scan digital images, e.g. from Computed Tomography (CT), for typical appearances and to highlight conspicuous sections, such as focal areas of lung nodules.

No abstract

Text Steganography has become a dominant research field in information sharing domain and many researches are being conducted to strengthen this area. Researches around the amount of secret message that could be stored in a given cover image is always critical for any steganography technique used to share the secret text. This research paper proposes an enhanced Least Significant Bit (eLSB) embedding technique in steganography, through which the quality of cover image is improved, when compared to typical LSB algorithm used in steganography. The proposed method employs in spatial domain and it does the secret message encoding in two phases. The first phase generates the metadata and embeds the header information in first few bytes of cover image and then the following phase takes care of processing secret message and storing the secret message in cover image using an optimized way, which is possible through analyzing secret text's character sequences. Proposed work results into occupying lesser space for the given secret text in cover image and hence leads to the better stego image quality than existing LSB algorithms. As the algorithm works on optimizing secret message during embedding phase itself, this technique enables high capacity embedding rate, additional security due to secret message preprocessing and enhanced cover image quality. The results are compared with LSB algorithm and compared to Peak Signal to Noise Ratio (PSNR), Mean Square Error (MSE) and Root Mean Square Error (RMSE) values to prove the proposed algorithm performs better on secret text embedding in cover image.

No abstract