Description

In this process binary rotation invariant and noise tolerant (BRINT) has been proposed which is a very fast, compact and also more accurate while illumination variations, noise and rotation changes. Texture is a characteristic of all natural surfaces of natural images. Texture recognition process is an important role for image processing. The texture classification problem focuses on the feature extraction of a particular image. For feature extraction local binary pattern (LBP) approach is commonly used. Binary Rotation Invariant and Noise Tolerant (BRINT) approach is proposed which based on the concept of local binary pattern (LBP) and Completed Local Binary Pattern (CLBP). This proposed algorithm not only provide accurate solution and also performed significantly and consistently better in presence of noise due to its high distinctiveness and robustness. This method used for different level of noise such as Gaussian, salt and pepper, and speckle noise. It is highly discriminative, has low computational complexity, is highly robust to noise and rotation, and allows for compactly encoding a number of scales and arbitrarily large circular neighborhoods. These approach overcome the limitation such as the instability of the uniform patterns, the lack of noise robustness, the inability to encode a large number of different local neighborhoods, an incapability to cope with large local neighborhoods, and high dimensionality. Texture classification process involves two phases: the learning phase and the recognition phase which is performed by SVM classifier. In the learning phase, the target is to build a model for the texture content of each texture class present in the training data, which generally comprises of images with known class labels. The texture content of the training images is captured with the chosen texture analysis method, which yields a set of textural features for each image. In our process snake texture has been taken and processed. >