Remote sensing performance tends to many features which are including change detection, ortho rectification, spectral analysis; image classification depends on the pixel based on reflectance into different land cover classes. It can be used to read specialized file formats that contain sensor image data, georeferencing information, and sensor Meta data. We have presented a new method for remote sensing image segmentation, which utilizes both spectral and texture information. Remote sensing image is taken as the input and converted into the gray scale image. Then the gray scale image is filtered by using Laplacian of Gaussian (LOG) filters. After that, the features are enhanced by using local spectral histogram. Then we have clustered the image using k-mean clustering. Moreover, the clustered image is segmented by using RGB colors. The SVD is calculated for error estimation and plot in the graph. The overall performance is good. Linear filters are used to provide enhanced spatial patterns. For each pixel location, we have computed combined spectral and texture features using local spectral histograms, which concatenate local histograms of all input bands. We have regarded each feature as a linear combination of several representative features, each of which corresponds to a segment. Segmentation is given by estimating combination weights, which indicate segment ownership of pixels. We have presented segmentation solutions where representative features are either known or unknown. We also show that feature dimension scan be greatly reduced via subspace projection. The scale issue is investigated, and an algorithm is presented to automatically select proper scales, which does not require segmentation at multiple scale levels.