Here we address the novel technique in CBIR (content based image retrieval). Here we use the method called Biased Discriminant Euclidean Embedding (BDEE).The parameterizes samples in the original high-dimensional ambient space to discover the intrinsic coordinate of image low-level visual features. We will find a low-dimensional subspace of the feature space, such that the positive and negative samples are well separated. So it will prevent from false retrieval. Here we extract the color feature, shape feature and texture feature. Color feature will be extracted by hue, saturation, value and color coherence vector. We extract the shape feature by the Gabor feature algorithm. Then we extract the texture feature by GLCM gray level co-occurrence matrix features. After extracting the feature we find the Euclidean distance between the query image and database images. Minimum distance between the images will be retrieved from the database. Retrieval will be done by the relevance feedback method.