International Journal of Multimedia Information Retrieval https://doi.org/10.1007/s13735-020-00200-3 TRENDS AND SURVEYS Recent advances in local feature detector and descriptor: a literature survey Khushbu Joshi 1,2 · Manish I. Patel 3 Received: 22 May 2020 / Revised: 6 October 2020 / Accepted: 16 October 2020 © Springer-Verlag London Ltd., part of Springer Nature 2020 Abstract The computer vision system is the technology that deals with identifying and detecting the objects of a particular class in digital images and videos. Local feature detection and description play an essential role in many computer vision applications like object detection, object classification, etc. The accuracy of these applications depends on the performance of local feature detectors and descriptors used in the methods. Over the past decades, new algorithms and techniques have been introduced with the development of machine learning and deep learning techniques. The machine learning techniques can lead the work to the next level when sufficient data is provided. Deep learning algorithms can handle a large amount of data efficiently. However, this may raise questions in a researcher’s mind about selecting the best algorithm and best method for a particular application to increase the performance. The selection of the algorithms highly depends on the type of application and amount of data to be handled. This encouraged us to write a comprehensive survey of local image feature detectors and descriptors from state-of-the-art to the recent ones. This paper presents feature detection and description methods in the visible band with their advantages and disadvantages. We also gave an overview of current performance evaluations and benchmark datasets. Besides, the methods and algorithms are described to find the features beyond the visible band. Finally, we concluded the survey with future directions. This survey may help researchers and serve as a reference in the field of the computer vision system. Keywords Computer vision system · Local feature detector · Local feature descriptor · Multispectral image 1 Introduction Image feature detectors and descriptors have become a vital tool over the last decades in many applications like object tracking [76,81], 3-D imaging [73], mobile augmented real- ity [104], image matching [110], object detection [117] and image registration [80]. An image feature is a piece of information extracted from an image that represents a more thorough understanding of the image. Image features are classified into two categories: global features and local features. Global features give infor- B Khushbu Joshi skhushi86@gmail.com Manish I. Patel manish.i.patel@nirmauni.ac.in 1 Sankalchand Patel Univesity, Visanagar, India 2 LDRP Institute of Technology and Research, Gandhinagar, India 3 Nirma University, Ahmedabad, India mation about the entire image. The global feature vector contains information about the image like shape, size, color, histogram, etc. The local features concentrate on the specific or exciting part of an image. The local feature vectors contain information like shape, color, histogram, etc. of the exciting part of an image [38]. Figure 1 shows the global and local features representation. 1.1 Properties of the ideal local features The following properties are essential for an efficient feature detector in computer vision applications [110]: – Robustness: detected feature locations should be inde- pendent of different geometric transformations. – Repeatability: detected features can be repeated under a variety of viewing conditions. – Accuracy: detected features accurately (same pixel loca- tions). 123