Robust object recognition using a color co-occurrence histogram and the spatial relations of image patches

2009 ◽  
Vol 13 (2) ◽  
pp. 488-492 ◽  
Author(s):  
Heebeom Bang ◽  
Sanghoon Lee ◽  
Dongjin Yu ◽  
Il Hong Suh
Keyword(s):  
Object Recognition ◽  
Spatial Relations ◽  
Image Patches

OBJECT RECOGNITION BASED ON BAG OF FEATURES AND A NEW LOCAL PATTERN DESCRIPTOR

2014 ◽  
Vol 28 (08) ◽  
pp. 1455010 ◽  
Author(s):  
CAROLINA TOLEDO FERRAZ ◽  
OSMANDO PEREIRA ◽  
MARCOS VERDINI ROSA ◽  
ADILSON GONZAGA
Keyword(s):  
Object Recognition ◽  
Effective Means ◽  
Recognition System ◽  
Scale Invariant ◽  
Image Scaling ◽  
Bag Of Features ◽  
Image Patches ◽  
Image Pixels ◽  
Scale Invariant Feature ◽  
Local Image

Bag of Features (BoF) has gained a lot of interest in computer vision. Visual codebook based on robust appearance descriptors extracted from local image patches is an effective means of texture analysis and scene classification. This paper presents a new method for local feature description based on gray-level difference mapping called Mean Local Mapped Pattern (M-LMP). The proposed descriptor is robust to image scaling, rotation, illumination and partial viewpoint changes. The training set is composed of rotated and scaled images, with changes in illumination and view points. The test set is composed of rotated and scaled images. The proposed descriptor more effectively captures smaller differences of the image pixels than similar ones. In our experiments, we implemented an object recognition system based on the M-LMP and compared our results to the Center-Symmetric Local Binary Pattern (CS-LBP) and the Scale-Invariant Feature Transform (SIFT). The results for object classification were analyzed in a BoF methodology and show that our descriptor performs better compared to these two previously published methods.

Coordination of what and where in Visual Attention

Perception ◽  
1993 ◽  
Vol 22 (11) ◽  
pp. 1261-1270 ◽  
Author(s):  
John Duncan
Keyword(s):  
Object Recognition ◽  
Visual Attention ◽  
Divided Attention ◽  
Visual Information ◽  
Functional Relationship ◽  
Human Subjects ◽  
Visual Display ◽  
Spatial Relations ◽  
Cortical Areas ◽  
Cortical System

Performance often suffers when two visual discriminations must be made concurrently (‘divided attention’). In the modular primate visual system, different cortical areas analyse different kinds of visual information. Especially important is a distinction between an occipitoparietal ‘where?’ system, analysing spatial relations, and an occipitotemporal ‘what?’ system responsible for object recognition. Though such visual subsystems are anatomically parallel, their functional relationship when ‘what?’ and ‘where?’ discriminations are made concurrently is unknown. In the present experiments, human subjects made concurrent discriminations concerning a brief visual display. Discriminations were either similar (two ‘what?’ or two ‘where?’ discriminations) or dissimilar (one of each), and concerned the same or different objects. When discriminations concerned different objects, there was strong interference between them. This was equally severe whether discriminations were similar—and therefore dependent on the same cortical system—or dissimilar. When concurrent ‘what?’ and ‘where?’ discriminations concerned the same object, however, all interference disappeared. Such results suggest that ‘what?’ and ‘where?’ systems are coordinated in visual attention: their separate outputs can be used simultaneously without cost, but only when they concern one object.

215 Object recognition using the compositions of image patches

2011 ◽  
Vol 2011.49 (0) ◽  
pp. 61-62
Author(s):  
Jyun_ichi Katsura ◽  
Katsunobu Konishi
Keyword(s):  
Object Recognition ◽  
Image Patches
Sign in / Sign up

Export Citation Format

Share Document