Visual graph modeling for scene recognition and mobile robot localization

Pham, Trong-Ton; Mulhem, Philippe; Maisonnasse, Loïc; Gaussier, Éric; Lim, Joo‐Hwee

doi:10.1007/s11042-010-0598-8

Cited by 7 publications

(7 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is estimated that 75% of the information received by a human is visual. One of the main application of using color as a feature vector is in Agriculture (Lian et al, 2012), Trademark (Phan and Androutsos, 2009) and Robotic vision (Trong et al, 2012).…”

Section: Necessity Of Color In Cbirmentioning

confidence: 99%

Color Perception Histogram for Image Retrieval Using Multiple Similarity Measures

Malini¹

2014

Journal of Computer Science

View full text Add to dashboard Cite

This study aims to increase the retrieval efficiency of proposed image retrieval system on the basis of color content. A new idea of feature extraction based on color perception histogram is proposed. First, the color histogram is constructed for HSV image. Secondly, the true color and grey color components are identified based on hue and intensity. The weight for true and grey color components is calculated using NBS distance. An updated histogram is constructed using weighted true and grey color values. The color features extracted from the updated histogram of query image and for all the images in image database are compared with existing color histogram based technique by using multiple similarity measures. Experimental results show that proposed image retrieval based on the color perception histogram gives higher retrieval performance in terms of high average precision and average recall with less computational complexity.

show abstract

Section: Necessity Of Color In Cbirmentioning

confidence: 99%

Color Perception Histogram for Image Retrieval Using Multiple Similarity Measures

Malini¹

2014

Journal of Computer Science

View full text Add to dashboard Cite

show abstract

“…Also, human eyes are sensitive to edge features for object recognition. Several algorithms have been applied for edge detection using different 1 Hue Saturation Value 2 Cyan Magneta Yellow blacK 3 http://wwwqbic.almaden.ibm.com/ methods [Harris & Stephens 1988, Ziou & Tabbone 1998], such as, Prewitt and Sobel mask, Canny filter, or Laplacians of Gaussian filters, etc. As shown in Figure 2.5, edge detection process preserves only the important information on the contours of the object.…”

Section: Edge Histogrammentioning

confidence: 99%

“…In [Marr 1982], Marr described the three layers of a classical paradigm in machine vision: the processing layer (1), the mapping layer (2), the high-level interpretation layer (3) (detailed in Figure 2.1). These three layers can be aligned to the three levels of image representation in CBIR, namely feature layer (low level), conceptual layer (middle level) and semantics layer (high level).…”

Section: Introductionmentioning

confidence: 99%

Modèle de graphe et modèle de langue pour la reconnaissance de scènes visuelles

Pham¹,

Maisonnasse²,

Mulhem³

et al. 2010

Document numérique

Self Cite

View full text Add to dashboard Cite

Content-based image indexing and retrieval (CBIR) system needs to consider several types of visual features and spatial information among them (i.e., different point of views) for better image representation. This thesis presents a novel approach that exploits an extension of the language modeling approach from information retrieval to the problem of graph-based image retrieval. Such versatile graph model is needed to represent the multiple points of views of images. This graph-based framework is composed of three main stages:Image processing stage aims at extracting image regions from the image. It also consists of computing the numerical feature vectors associated with image regions.Graph modeling stage consists of two main steps. First, extracted image regions that are visually similar will be grouped into clusters using an unsupervised learning algorithm. Each cluster is then associated with a visual concept. The second step generates the spatial relations between the visual concepts. Each image is represented by a visual graph captured from a set of visual concepts and a set of spatial relations among them.Graph retrieval stage is to retrieve images relevant to a new image query. Query graphs are generated following the graph modeling stage. Inspired by the language model for text retrieval, we extend this framework for matching the query graph with the document graphs from the database. Images are then ranked based on the relevance values of the corresponding image graphs.Two instances of the visual graph model have been applied to the problem of scene recognition and robot localization. We performed the experiments on two image collections: one contained 3,849 touristic images and another composed of 3,633 images captured by a mobile robot. The achieved results show that using visual graph model outperforms the standard language model and the Support Vector Machine method by more than 10% in accuracy.

show abstract

“…Graph representation [12][13][14][15] also presents a natural way to encode the spatial relation between local appearances. In [12], an image dataset is first modelled by a graph grouping similar visual features with the k-means algorithm.…”

Section: Introductionmentioning

confidence: 99%

“…In [12], an image dataset is first modelled by a graph grouping similar visual features with the k-means algorithm. Then, the spatial relations between the visual words are identified.…”

Section: Introductionmentioning

confidence: 99%

Bag of frequent subgraphs approach for image classification

Mejdoub

Aoun

Amar

2015

IDA

View full text Add to dashboard Cite

The bag of words approach describes an image as a histogram of visual words. Therefore, the structural relation between words is lost. Since graphs are well adapted to represent these structural relations, we propose, in this paper, an image classification framework which draws benefit from the efficiency of the graph in modeling structural information and the good classification performances given by the bag of words method. For each image in the dataset, a graph is created by modeling the spatial relations between dense local patches. Thus, we obtain a graph dataset. From the graph dataset, we select the most frequent subgraphs to construct the bag of subgraphs (BoSG) and we associate to each image a subgraph histogram that describes its visual content. For experiments, we have used the two challenging datasets: 15 Scenes and Pascal VOC 2007. Experimental results show that the proposed method outperforms the bag of words and the spatial pyramid models in terms of recognition rate.

show abstract

Visual graph modeling for scene recognition and mobile robot localization

Cited by 7 publications

References 27 publications

Color Perception Histogram for Image Retrieval Using Multiple Similarity Measures

Color Perception Histogram for Image Retrieval Using Multiple Similarity Measures

Modèle de graphe et modèle de langue pour la reconnaissance de scènes visuelles

Bag of frequent subgraphs approach for image classification

Contact Info

Product

Resources

About