CSIFT Based Locality-constrained Linear Coding for Image Classification
This work addresses misclassification issues in image classification for vision tasks by incorporating color information, but it is incremental as it builds on existing methods like SIFT and LLC.
The paper tackled the problem of misclassification in image classification due to ignoring color information by enhancing traditional SIFT descriptors with color variants, resulting in approximately 3% accuracy improvement on Caltech-101 and 4% on Caltech-256.
In the past decade, SIFT descriptor has been witnessed as one of the most robust local invariant feature descriptors and widely used in various vision tasks. Most traditional image classification systems depend on the luminance-based SIFT descriptors, which only analyze the gray level variations of the images. Misclassification may happen since their color contents are ignored. In this article, we concentrate on improving the performance of existing image classification algorithms by adding color information. To achieve this purpose, different kinds of colored SIFT descriptors are introduced and implemented. Locality-constrained Linear Coding (LLC), a state-of-the-art sparse coding technology, is employed to construct the image classification system for the evaluation. The real experiments are carried out on several benchmarks. With the enhancements of color SIFT, the proposed image classification system obtains approximate 3% improvement of classification accuracy on the Caltech-101 dataset and approximate 4% improvement of classification accuracy on the Caltech-256 dataset.