Dimension Reduction of the SIFT descriptor and its Object Recognition
نویسنده
چکیده
..................................................................................................................................... 3 Introduction ................................................................................................................................ 4 Stage (I) ....................................................................................................................................... 6 Overview: ................................................................................................................................ 6 (1.1) Brief introduction to OpenCV .......................................................................................... 6 (1.2) A simple SIFT feature matching Experiment using brute force approach .......................... 7 (1.3) Finding “Strong” SIFT Keypoints....................................................................................... 9 (1.4) Compare Average Models ............................................................................................. 12 (1.5) Compute Probability Density Function and Confusion Probabilities ............................... 14 Stage (2) .................................................................................................................................... 17 Overview ........................................................................................................................... 17 (2.1) SIFT keypoints ranking system ....................................................................................... 17 (2.2) Reduce dimensionality of SIFT feature descriptors using t-SNE ...................................... 19 (2.3) A simple object classifier ............................................................................................... 22 Summary and Possible Future Works ........................................................................................ 24 Reference ................................................................................................................................. 24 Appendix ................................................................................................................................... 26 Functional Requirements: ..................................................................................................... 26 Object Identification: ......................................................................................................... 26 Program Input: .................................................................................................................. 26 Program Output: ............................................................................................................... 27 Non-functional Requirements: .............................................................................................. 27 Object recognition ............................................................................................................. 27 Development/Usage platform ........................................................................................... 27
منابع مشابه
Dimension Reduction and Classification Methods for Object Recognition in Vision
This paper addresses the challenging task of recognizing and locating objects in natural images. In computer vision, many successful approaches to object recognition use local image descriptors. Such descriptors do not require segmentation, in addition they are robust to partial occlusion and invariant to image transformations (particularly scale changes). Among the existing descriptors, a rece...
متن کاملPerformance Evaluation of SIFT - Based Descriptors for Object Recognition
Object recognition has become one of the most active research topics in computer vision in recent years. The set of features extracted from the training image is critical for good object recognition performance. The Scale Invariant Feature Transform (SIFT) was proposed by David Lowe in 1999; the SIFT features are local and effective for object recognition. In this paper we conducted a survey of...
متن کاملUsing Gradient Features from Scale-invariant Keypoints on Face Recognition
As the individual identification, access control and security appliance issues attract much attention, face recognition applications are more and more popular. The challenge of face recognition is that the performance is mainly constrained by the variations of illumination, expression, pose and accessory. And most algorithms which were proposed in recent years focused on how to conquest these c...
متن کاملColor orthogonal local binary patterns combination for image region description
Visual content description is a key issue for machine-based image analysis and understanding. A good visual descriptor should be both discriminative enough and computationally efficient while possessing some properties of robustness to viewpoint changes and lighting condition variations. In this paper, we propose several new local descriptors based on color orthogonal local binary patterns comb...
متن کاملDescription of interest regions with local binary patterns
This paper presents a novel method for interest region description. We adopted the idea that the appearance of an interest region can be well characterized by the distribution of its local features. The most well-known descriptor built on this idea is the SIFT descriptor that uses gradient as the local feature. Thus far, existing texture features are not widely utilized in the context of region...
متن کامل