In the last post, I talked about HOG, which is a very successfully used image feature used in object detection and identification. Closely related are the binary descriptors, which encode local characteristic of image intensity values in a binary code, particularly, around a key point. These codes in two locations in the same image or different image can be matched to find similarities (like template matching). There are quite a few good descriptors now: BRIEF , ORB , BRISK , FREAK . They all are related to Local Binary Pattern (LBP)[3,4], which is a particular case of Texture Spectrum model [1,2].
The binary descriptors are recent advances (not so recent yet!) and their research was inspired by the success of SIFT  and SURF , which are patch descriptors, again used to match similar key points in different images/locations. However, SIFT and SURF are slow and patent protected.
A good introduction to the above descriptors can be found in Gil’s computer vision blog .
Understanding the descriptors and their applications is good. But the most recent developments in the literature indicates a different trend. The descriptors described above are all hand-designed. That is, they were discovered or designed with the help of years of experience and intuition. On the other hand, recent developments, deep learning networks, gives us a way to intelligently automate this process: the possibility that machine learns the relevant features to detect and identify objects itself, with very little human intervention! Yes, that is all about deep learning and deep learning network. I’ll update as I progress through the deep learning literature. However, I would like to mention that a good overview/starting point may be Prof. Yoshua Bengio‘s monograph on deep learning . You can also search for online courses or youtube lectures on deep learning.
 DC. He and L. Wang (1990), “Texture Unit, Texture Spectrum, And Texture Analysis”, Geoscience and Remote Sensing, IEEE Transactions on, vol. 28, pp. 509 – 512.
 L. Wang and DC. He (1990), “Texture Classification Using Texture Spectrum”, Pattern Recognition, Vol. 23, No. 8, pp. 905 – 910.
 T. Ojala, M. Pietikäinen, and D. Harwood (1994), “Performance evaluation of texture measures with classification based on Kullback discrimination of distributions”, Proceedings of the 12th IAPR International Conference on Pattern Recognition (ICPR 1994), vol. 1, pp. 582 – 585.
 T. Ojala, M. Pietikäinen, and D. Harwood (1996), “A Comparative Study of Texture Measures with Classification Based on Feature Distributions”, Pattern Recognition, vol. 29, pp. 51-59.
 Calonder, Michael, et al. “BRIEF: Binary robust independent elementary features.” Computer Vision–ECCV 2010. Springer Berlin Heidelberg, 2010. 778-792.
 Rublee, Ethan, et al. “ORB: an efficient alternative to SIFT or SURF.” Computer Vision (ICCV), 2011 IEEE International Conference on. IEEE, 2011.
 Leutenegger, Stefan, Margarita Chli, and Roland Y. Siegwart. “BRISK: Binary robust invariant scalable keypoints.” Computer Vision (ICCV), 2011 IEEE International Conference on. IEEE, 2011.
 Alahi, Alexandre, Raphael Ortiz, and Pierre Vandergheynst. “FREAK: Fast retina keypoint.” Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on. IEEE, 2012.
 Lowe, David G. “Object recognition from local scale-invariant features.”Computer vision, 1999. The proceedings of the seventh IEEE international conference on. Vol. 2. Ieee, 1999.
 Bay, Herbert, Tinne Tuytelaars, and Luc Van Gool. “Surf: Speeded up robust features.” Computer Vision–ECCV 2006. Springer Berlin Heidelberg, 2006. 404-417.