TERZIĆ: SHAPE DETECTION WITH NEAREST NEIGHBOUR CONTOUR FRAGMENTS 1 Shape Detection with Nearest Neighbour Contour Fragments
نویسندگان
چکیده
We present a novel method for shape detection in natural scenes based on incomplete contour fragments and nearest neighbour search. In contrast to popular methods which employ sliding windows, chamfer matching and SVMs, we characterise each contour fragment by a local descriptor and perform a fast nearest-neighbour search to find similar fragments in the training set. Based on this idea, we show how to learn robust object models from training images, to generate reliable object hypotheses, and to verify them. Despite its extreme simplicity and speed, our method produces competitive detection results on the challenging ETHZ dataset.
منابع مشابه
Shape Detection with Nearest Neighbour Contour Fragments
Shape is probably the single most important feature for object detection and much research has gone into developing deformable shape models. However, contours extracted by bottom-up edge detectors are notoriously unreliable, especially in natural images. In this paper, we present a very simple, yet powerful method for model creation, hypothesis generation, and hypothesis verification, which is ...
متن کاملApplication of Edge Detection on Large Lump Detection
Detecting large lumps of oil sand is a critical step which protects exploitation facilities from jamming. This report presents a method that detects large lumps with edge detection and edge classification. The approach applies Gaussian based local scale control algorithm to detect edges in oil sands, then extracts intensity features as well as geometry features for edge classification. Trained ...
متن کاملDiscriminative Learning of Contour Fragments for Object Detection
The goal of this work is to discriminatively learn contour fragment descriptors for the task of object detection. Unlike previous methods that incorporate learning techniques only for object model generation or for verification after detection, we present a holistic object detection system using solely shape as underlying cue. In the learning phase, we interrelate local shape descriptions (frag...
متن کاملContour based object detection using part bundles
In this paper we propose a novel framework for contour based object detection from cluttered environments. Given a contour model for a class of objects, it is first decomposed into fragments hierarchically. Then, we group these fragments into part bundles, where a part bundle can contain overlapping fragments. Given a new image with set of edge fragments we develop an efficient voting method us...
متن کاملFace Recognition Using Contour-Based Multiscale Distance Matrix
Face Recognition is an emerging approach in the recent years. In this paper, the formulation of a face recognition approach using contour-based shape descriptor named Multiscale Distance Matrix (MDM) is developed using the concept of inner-distance in the distance matrix instead of the Euclidean distance. In the proposed scheme, first the similarity in the shape of the face is found by taking a...
متن کامل