This chapter discusses the state-of-the-art methods in computer vision for several tasks such as object recognition, texture analysis, and optical character recognition. Most of the state-of-the-art approaches are based on patches or image descriptors, but other approaches, such as those based on deep learning, have shown impressive levels of performance. Image descriptors, which form another class of local image features besides patches, are also presented in this chapter. Since this book is mainly focused on learning based on similarity, an entire section is dedicated to image distance measures.
CITATION STYLE
Ionescu, R. T., & Popescu, M. (2016). State-of-the-Art Approaches for Image Classification. In Advances in Computer Vision and Pattern Recognition (pp. 41–52). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-319-30367-3_3
Mendeley helps you to discover research relevant for your work.