A statistical method for 3D object detection applied to faces and cars

Schneiderman, Henry; Kanade, Takeo

doi:10.1109/cvpr.2000.855895

Cited by 793 publications

(611 citation statements)

References 9 publications

Supporting

Mentioning

606

Contrasting

Unclassified

Order By: Relevance

“…Some images are specifically taken for this purpose. The other images are taken from the Combined MIT/CMU Test Images [4] [9] or downloaded from the internet. The test images are all grayscale images (or are colour images converted into grayscale) but have various spatial resolutions and quality.…”

Section: Experiments Setup and Resultsmentioning

confidence: 99%

Section: B Face Classification Sub-systemmentioning

confidence: 99%

“…The authors in [2] have also proposed another possible approach, by detecting the presence of objects, like nose and nostrils, which are normally present in human faces. Finally, another approach that has been proposed is the use of statistical models of the facial area and non-facial areas [4]. In our previous works [5][6], we have shown that the use of 1-dimensional Haar wavelet coefficients as a discriminating feature to detect faces can give a satisfactory result which are robust againts variations in background, illumination and subject expression.…”

mentioning

confidence: 99%

“…The input images for the face classification sub-system are 64 × 64 pixel 8-bit grayscale images taken from the output of the face detection sub-system. The Gaussian kernel [4] was used as the nonlinear mapping ϕ(⋅):The penalty to the error C used in this paper is 50 and the parameter of the kernel function σ used in this paper is 90. These parameter values were determined empirically by means of 2-fold cross validation using 30 subjects from the Video, Image, and Signal Processing (VISiO) laboratory Satya Wacana Christian University (SWCU) multiview face database that will be further explained in Section V. …”

mentioning

confidence: 99%

See 3 more Smart Citations

A Frontal Pose Face Detection and Classification System Based on Haar Wavelet Coefficients and Support Vector Machine

Setyawan¹,

Timotius²

2011

IJIEE

View full text Add to dashboard Cite

Abstract-This paper presents an integrated face detection and classfication system for faces with frontal pose. The face detection sub-system is based on Haar wavelet coefficients and the face classification sub-system is based on support vector machines. The proposed system is trained using the VISiO multi-view face database and is tested using the commonly used test sets. Our experiments show that the proposed face detection sub-system has a 94.8% detection rate while the face classification sub-system has a 68.1% classification rate.Index Terms-Face detection, face classification, haar wavelet, support vector machine. I. INTRODUCTIONNowadays, there are a lot of applications that rely on the classification of human faces. For example, such a system can be employed as a part of a security system that allows access to a certain area only to persons that are members of a certain group. Another example is a surveillance system that can give an alert to law enforcement agencies of the presence of people that are known to belong to terrorist groups. Each of these applications relies on the integration of a face detection system and a face classification system. The face detection system is used to locate the facial area within the input image while the face classification system is used to determine to which group the detected person belongs.Ideally, a face detection system should be able to locate all the faces in a digital image, regardless of position, scale, orientation, age, expression, illumination conditions and image content [1]. There are many discriminating features that can be used to detect faces proposed in the literature. For example, one can use human skin colour detection to locate faces [1] [2]. Another approach is to use template matching methods [3]. The authors in [2] have also proposed another possible approach, by detecting the presence of objects, like nose and nostrils, which are normally present in human faces. Finally, another approach that has been proposed is the use of statistical models of the facial area and non-facial areas [4]. In our previous works [5][6], we have shown that the use of 1-dimensional Haar wavelet coefficients as a discriminating feature to detect faces can give a satisfactory result which are robust againts variations in background, illumination and subject expression.Face classification system is a machine that is used to classify people based on their face. Support Vector Machines (SVM) is one of the possible methods used to classify faces. SVM is well-known because this method utilized optimalization approach to construct a separating hyperplane as a decision surface [7]. This hyperplane is constructed in a high-dimensional feature space by using a nonlinear mapping. By the means of SVM, the face classification system is expectantly able to construct a decision surface which maximizes the margin of separation between the face images among the two groups of people.This paper presents a system that could detect the areas of an image which contain faces and subsequen...

show abstract

Section: Experiments Setup and Resultsmentioning

confidence: 99%

Section: B Face Classification Sub-systemmentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

A Frontal Pose Face Detection and Classification System Based on Haar Wavelet Coefficients and Support Vector Machine

Setyawan¹,

Timotius²

2011

IJIEE

View full text Add to dashboard Cite

show abstract

“…3D model-based methods ( [20]) are successful when we can describe accurate geometric models for the object. Appearance based matching approaches are based on searching the image at different locations and different scales for best match for object 'template" where the object template can be learned from training data and act as a local classifier [18,15]. Such approaches are highly successful in modeling objects with wide within-class appearance variations such as in face detection [18, 15] but they are limited when the within-class geometric variations are large, such as detecting a motorbike.…”

Section: Introductionmentioning

confidence: 99%

A Statistically Selected Part-Based Probabilistic Model for Object Recognition

Zhao

Elgammal

2006

Advances in Machine Vision, Image Processing, and Pattern Analysis

View full text Add to dashboard Cite

Abstract. In an object recognition task where an image is represented as a constellation of image patches, often many patches correspond to the cluttered background. If such patches are used for object class recognition, they will adversely affect the recognition rate. In this paper, we present a statistical method for selecting the image patches which characterize the target object class and are capable of discriminating between the positive images containing the target objects and the complementary negative images. This statistical method select those images patches from the positive images which, when used individually, have the power of discriminating between the positive and negative images in the evaluation data. Another contribution of this paper is the part-based probabilistic method for object recognition. This Bayesian approach uses a common reference frame instead of reference patch to avoid the possible occlusion problem. We also explore different feature representation using PCA an 2D PCA. The experiment demonstrates our approach has outperformed most of the other known methods on a popular benchmark data set while approaching the best known results.

show abstract

Digital Photo Forensics

Krawetz¹

2015

Handbook of Digital Imaging

View full text Add to dashboard Cite

The abundance of graphics applications has made it easy for anyone to modify digital pictures. However, modified pictures can cause problems for fields where altered photographs may give the wrong impression. Issues arise when altered images are used to convey misleading news, alter a product's performance in advertisements and scientific research, or are associated with identity theft or court proceedings. Forensic imaging provides algorithms, tools, and techniques for detecting image tampering. This chapter focuses on the problem space and some of the more common approaches to address problems in this field.

show abstract

A statistical method for 3D object detection applied to faces and cars

Cited by 793 publications

References 9 publications

A Frontal Pose Face Detection and Classification System Based on Haar Wavelet Coefficients and Support Vector Machine

A Frontal Pose Face Detection and Classification System Based on Haar Wavelet Coefficients and Support Vector Machine

A Statistically Selected Part-Based Probabilistic Model for Object Recognition

Digital Photo Forensics

Contact Info

Product

Resources

About