检索结果-内蒙古大学图书馆

Proceedings of the 2019 2nd Artificial Intelligence and Cloud Computing Conference

作者： Taha H. Rassem Nasrin M. Makbol Bee Ee Khoo Universiti Malaysia Pahang School of Electrical and Electronic Engineering Universiti Sains Malaysia Penang Malaysia

ISBN: (纸本)9781450372633

object class recognition has recently become one of the most popular research fields. This is due to its importance in many applications such as image classification, retrieval, indexing, and searching. The main aim of object class recognition is determining how to make computers understand and identify automatically which object or scene is being displayed on the image. Despite a lot of efforts that have been made, it still considered as one of the most challenging tasks, mainly due to inter-class variations and intra-class variations like occlusion, background clutter, viewpoint changes, pose, scale and illumination. Feature extraction is one of the important steps in any object class recognition system. Different image features are proposed in the literature review to increase categorisation accuracy such as appearance, texture, shape descriptors. In this paper, we propose to combine different descriptors which are dense colour scale-invariant feature transform (dense colour SIFT) as appearance descriptors with different texture descriptors. The colour completed local binary pattern (CCLBP) and completed local ternary pattern (CLTP) are integrated with dense colour SIFT due to the importance of the texture information in the image. Using different pattern sizes to extract the CLTP and CCLBP texture descriptors will help to find dense texture information from the image. Bag of features is also used in the proposed system with each descriptor while the late fusion strategy is used in the classification stage. The proposed system achieved high recognition accuracy rate when applied in some datasets, namely SUN-397, OT4N, OT8, and Event sport datasets, which accomplished 38.9%, 95.9%, 89.02%, and 88.167%, respectively.

关键词： object class recognition and Completed Local Ternary Pattern (CLTP) Feature extraction Scale-invariant Feature Transform(SIFT) Colour Completed Local Binary Pattern (CCLBP)

来源：评论

学校读者我要写书评

暂无评论

Local appearance modeling for objects class recognition

引用

PATTERN ANALYSIS AND APPLICATIONS 2019年第2期22卷 439-455页

作者： Taffar, Mokhtar Miguet, Serge Univ Jijel Dept Comp Sci BP 98 Ouled Aissa 18000 Jijel Algeria Univ Lyon 2 Univ Lyon UMR CNRS 5205 LIRIS 5 Ave Pierre Mendes FranceBat C 123 F-69676 Lyon France

In this work, we propose a new formulation of the objects modeling combining geometry and appearance;it is useful for detection and recognition. The object local appearance location is referenced with respect to an invariant which is a geometric landmark. The appearance (shape and texture) is a combination of Harris-Laplace descriptor and local binary pattern (LBP), all being described by the invariant local appearance model (ILAM). We use an improved variant of LBP traits at regions located by Harris-Laplace detector to encode local appearance. We applied the model to describe and learn object appearances (e.g., faces) and to recognize them. Given the extracted visual traits from a test image, ILAM model is carried out to predict the most similar features to the facial appearance: first, by estimating the highest facial probability and then in terms of LBP histogram-based measure, by computing the texture similarity. Finally, by a geometric calculation the invariant allows to locate an appearance in the image. We evaluate the model by testing it on different face images databases. The experiments show that the model results in high accuracy of detection and provides an acceptable tolerance to the appearance variability.

关键词： Invariant descriptors Local binary patterns Features matching Probabilistic learning Appearance modeling object class recognition Facial detection

来源：评论

学校读者我要写书评

暂无评论

Do Semantic Parts Emerge in Convolutional Neural Networks?

引用

INTERNATIONAL JOURNAL OF COMPUTER VISION 2018年第5期126卷 476-494页

作者： Gonzalez-Garcia, Abel Modolo, Davide Ferrari, Vittorio Univ Edinburgh Sch Informat IPAB Crichton St 10 Edinburgh EH8 9AB Midlothian Scotland

Semantic object parts can be useful for several visual recognition tasks. Lately, these tasks have been addressed using Convolutional Neural Networks (CNN), achieving outstanding results. In this work we study whether CNNs learn semantic parts in their internal representation. We investigate the responses of convolutional filters and try to associate their stimuli with semantic parts. We perform two extensive quantitative analyses. First, we use ground-truth part bounding-boxes from the PASCAL-Part dataset to determine how many of those semantic parts emerge in the CNN. We explore this emergence for different layers, network depths, and supervision levels. Second, we collect human judgements in order to study what fraction of all filters systematically fire on any semantic part, even if not annotated in PASCAL-Part. Moreover, we explore several connections between discriminative power and semantics. We find out which are the most discriminative filters for object recognition, and analyze whether they respond to semantic parts or to other image patches. We also investigate the other direction: we determine which semantic parts are the most discriminative and whether they correspond to those parts emerging in the network. This enables to gain an even deeper understanding of the role of semantic parts in the network.

关键词： CNNs for computer vision Semantic object parts object class recognition Analysis of CNNs

来源：评论

学校读者我要写书评

暂无评论

Face class Modeling based on Local Appearance for recognition 6

Face Class Modeling based on Local Appearance for Recognitio...

引用

6th International Conference on Pattern recognition Applications and Methods (ICPRAM)

作者： Taffar, Mokhtar Miguet, Serge Univ Jijel Comp Sc Dept BP 98 Ouled Aissa 18000 Jijel Algeria Univ Lyon LIRIS CNRS UMR 5205 5 Av Pierre Mendes France F-69676 Bron France

ISBN: (纸本)9789897582226

This work proposes a new formulation of the objects modeling combining geometry and appearance. The object local appearance location is referenced with respect to an invariant which is a geometric landmark. The appearance (shape and texture) is a combination of Harris-Laplace descriptor and local binary pattern (LBP), all is described by the invariant local appearance model (ILAM). We applied the model to describe and learn facial appearances and to recognize them. Given the extracted visual traits from a test image, ILAM model is performed to predict the most similar features to the facial appearance, first, by estimating the highest facial probability, then in terms of LBP Histogram-based measure. Finally, by a geometric computing the invariant allows to locate appearance in the image. We evaluate the model by testing it on different images databases. The experiments show that the model results in high accuracy of detection and provides an acceptable tolerance to the appearance variability.

关键词： Invariant Descriptors Local Binary Patterns Features Matching Probabilistic Matching Model Learning Appearance Modeling object class recognition Facial Detection

来源：评论

学校读者我要写书评

暂无评论

AN EVALUATION OF LOCAL IMAGE FEATURES FOR object class recognition

AN EVALUATION OF LOCAL IMAGE FEATURES FOR OBJECT CLASS RECOG...

引用

5th International Conference on Computer Vision Theory and Applications (VISAPP 2010)

作者： Islam, Saiful Sluzek, Andrzej Nanyang Technol Univ Sch Comp Engn Ctr Computat Intelligence Singapore 639798 Singapore

ISBN: (纸本)9789896740290

The use of local image features (LIP) for object class recognition is becoming increasingly popular. To better understand the suitability and power of existing LIFs for object class recognition, a simple but useful method is proposed in evaluation of such features. We have compared the performance of eight frequently used LIFs by the proposed method on two popular databases. We have used F-measure criterion for this evaluation. It is found that the individual performance of SURF and SIFT features are better than that of the global features on ETH-80* database with considerably lower number of training objects. However, it may not be good enough for more challenging object class recognition problem (e.g. Caltech-101(+)). The evaluation of LIFs suggests the requirement for further investigation of more complementary LIFs.

关键词： Local Image Feature object class recognition Nearest Neighbour classification

来源：评论

学校读者我要写书评

暂无评论

MULTI FEATURE BASED object class recognition

MULTI FEATURE BASED OBJECT CLASS RECOGNITION

引用

International Conference on Digital Image Processing

作者： Manshor, Noridayu Rajeswari, Mandava Ramachandram, Dhanesh Univ Sains Malaysia Sch Comp Sci Comp Vis Res Grp George Town 11800 Malaysia

ISBN: (纸本)9780769535654

In object class recognition, lots of past researches focused on the local descriptors such as SIFT to categorize the variation of objects belonging to the same category in different poses, sizes, and appearance. However, SIFT descriptors may produce poor result especially if the object does not have enough information of its texture features. Due to this problem, we hypothesize that the use multi feature may increase the performance of object class recognition. In this paper, we use additional global shape features, Fourier Descriptors combined with SIFT descriptors to help in improving the performance of object class recognition. The selection of shape features is chosen due to the objects are easier to describe based on this features from human perspective compare to other features. We have divided our experiments into two: Experiment E I is limited to the side view of bike, car, horse, and cow images whereas Experiment E2 consists of similar categories of dataset but in arbitrary views, rotations, and scales. The dataset we used in our experimentation are obtained from PASCAL, Weizmann and TU Darmstadt database. We assume that all objects are segmented manually before the feature extraction process. We validate our selection features using K-Means algorithm to evaluate the features for the purpose of object class recognition. Our results indicate that the combination of additional shape features together with SIFT descriptors performs better than using SIFT descriptors alone by up to 15% with limitation views of images.

关键词： object class recognition Fourier Descriptors SIFT multi feature

来源：评论

学校读者我要写书评

暂无评论

object class recognition and localization using sparse features with limited receptive fields

引用

INTERNATIONAL JOURNAL OF COMPUTER VISION 2008年第1期80卷 45-57页

作者： Mutch, Jim Lowe, David G. MIT Dept Brain & Cognit Sci Cambridge MA 02139 USA Univ British Columbia Dept Comp Sci Vancouver BC V6T 1W5 Canada

We investigate the role of sparsity and localized features in a biologically-inspired model of visual object classification. As in the model of Serre, Wolf, and Poggio, we first apply Gabor filters at all positions and scales;feature complexity and position/scale invariance are then built up by alternating template matching and max pooling operations. We refine the approach in several biologically plausible ways. Sparsity is increased by constraining the number of feature inputs, lateral inhibition, and feature selection. We also demonstrate the value of retaining some position and scale information above the intermediate feature level. Our final model is competitive with current computer vision algorithms on several standard datasets, including the Caltech 101 object categories and the UIUC car localization task. The results further the case for biologically-motivated approaches to object classification.

关键词： object class recognition ventral visual pathway sparsity localized features

来源：评论

学校读者我要写书评

暂无评论

object class recognition Using NEAT-evolved Artificial Neural Network

Object Class Recognition Using NEAT-evolved Artificial Neura...

引用

5th International Conference on Computer Graphics, Imaging and Visualization (CGIV)

作者： Hasanat, Mozaherul Hoque Abul Harun, Siti Zubaidah Ramachandran, Dhanesh Rajeswari, Mandava Univ Sains Malaysia Sch Comp Sci Comp Vis Res Grp George Town Malaysia

ISBN: (纸本)9780769533599

object class recognition is a highly challenging area in computer vision. and machine learning. In this paper;we introduce a novel approach to object class recognition using NeuroEvolution of Augmenting Topologies (NEAT) to evolve artificial neural networks (ANN) capable of taking advantage of the robust SIFT feature based descriptor histograms. We claim that NEAT can produce ANN classifier which exhibits outstanding ability, of learning from only a few training examples without sacrificing accuracy. Our empirical evaluations against the performance of state of the art statistical machine learning method such as support-vector machine show that NEAT-evolved ANN classifier outperforms by an average of 9.96% higher accuracy when presented with very small training set proving its superior ability to generalize its learning.

关键词： NEAT object class recognition SIFT NeuroEvolution

来源：评论

学校读者我要写书评

暂无评论

Learning a Part Vocabulary by Clustering Ensemble for object class recognition

Learning a Part Vocabulary by Clustering Ensemble for Object...

引用

第四届全国信息检索与内容安全学术会议

作者： Yang LINYUN~* Wen MING Zhuo QING Wang WENYUAN Department of Automation,Tsinghua University,Beijing 100084,China

In this paPer we present a novel method for object class recognition.A vocabulary of object parts is automatically constructed from sample images of the object class by random projection based clustering ensemble. Images are then represented using parts from this *** on this representation,the Sparse Network of Winnows(SNoW)learning architecture is employed to learn to recognize instances of the object *** results show that the method achieves high recognition accuracy on different data sets,and is highly robust to partial occlusion and background clutter.

关键词： object class recognition part-based representation SIFT part vocabulary clustering ensemble SNoW

来源：评论

学校读者我要写书评

暂无评论

A Bayesian approach for object classification based on clusters of SIFT local features

引用

EXPERT SYSTEMS WITH APPLICATIONS 2012年第2期39卷 1679-1686页

作者： Chang, Leonardo Duarte, Miriam M. Enrique Sucar, L. Morales, Eduardo F. Natl Inst Astrophys Opt & Elect Mexico City 72840 DF Mexico Adv Technol Applicat Ctr Havana Cuba

Several methods have been presented in the literature that successfully used SIFT features for object identification, as they are reasonably invariant to translation, rotation, scale, illumination and partial occlusion. However, they have poor performance for classification tasks. In this work, SIFT features are used to solve object class recognition problems in images using a two-step process. In its first step, the proposed method performs clustering on the extracted features in order to characterize the appearance of the different classes. Then, in the classification step, it uses a three layer Bayesian network for object class recognition. Experiments show quantitatively that clusters of SIFT features are suitable to represent classes of objects. The main contributions of this paper are the introduction of a Bayesian network approach in the classification step to improve performance in an object class recognition task, and a detailed experimentation that shows robustness to changes in illumination, scale, rotation and partial occlusion. (C) 2011 Elsevier Ltd. All rights reserved.

关键词： object class recognition Local features SIFT Clustering Bayesian networks

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：