scispace - formally typeset
Search or ask a question
Proceedings ArticleDOI

Self-similarity representation of Weber faces for kinship classification

TL;DR: A kinship classification algorithm that uses the local description of the pre-processed Weber face image to outperforms an existing algorithm and yields a classification accuracy of 75.2%.
Abstract: Establishing kinship using images can be utilized as context information in different applications including face recognition. However, the process of automatically detecting kinship in facial images is a challenging and relatively less explored task. The reason for this includes limited availability of datasets as well as the inherent variations amongst kins. This paper presents a kinship classification algorithm that uses the local description of the pre-processed Weber face image. A kinship database is also prepared that contains images pertaining to 272 kin pairs. The database includes images of celebrities (and their kins) and has four ethnicity groups and seven kinship groups. The proposed algorithm outperforms an existing algorithm and yields a classification accuracy of 75.2%.
Citations
More filters
Book ChapterDOI
01 Jan 2017
TL;DR: This chapter introduces a compact binary face descriptor (CBFD) method which learns face descriptors directly from raw pixels and presents a prototype-based discriminative feature learning (PDFL) method to learn mid-level discrim inative features with low-level descriptor for kinship verification.
Abstract: In this chapter, we discuss feature learning techniques for facial kinship verification. We first review two well-known hand-crafted facial descriptors including local binary patterns (LBP) and the Gabor feature. Then, we introduce a compact binary face descriptor (CBFD) method which learns face descriptors directly from raw pixels. Unlike LBP which samples small-size neighboring pixels and computes binary codes with a fixed coding strategy, CBFD samples large-size neighboring pixels and learn a feature filter to obtain binary codes automatically. Subsequently, we present a prototype-based discriminative feature learning(PDFL) method to learn mid-level discriminative features with low-level descriptor for kinship verification. Unlike most existing prototype-based feature learning methods which learn the model with a strongly labeled training set, this approach works on a large unsupervised generic set combined with a small labeled training set. To better use multiple low-level features for mid-level feature learning, a multiview PDFL (MPDFL) method is further proposed to learn multiple mid-level features to improve the verification performance.

1 citations


Cites background from "Self-similarity representation of W..."

  • ...Unlike most previous kinship verification work where low-level hand-crafted feature descriptors [12, 13, 15, 24, 34, 39, 47, 48, 50, 53, 54] such as local binary pattern (LBP) [2, 9] and Gabor features [31, 54] are employed for face representation, we expect to extract more semantic information from low-level features to better characterize the relation of face images for kinship verification....

    [...]

Proceedings ArticleDOI
23 Apr 2014
TL;DR: It is shown that the combined use of dynamic and spatio-temporal features extracted from spontaneous smiles significantly improves the state of the art.
Abstract: Automatic kinship verification methods are conventionally based on facial appearance. In contrast to all published material, in this paper, we explore the use of facial expression dynamics and spatio-temporal features for kinship verification from smile videos. It is shown that the combined use of dynamic and spatio-temporal features extracted from spontaneous smiles significantly improves the state of the art.

1 citations


Additional excerpts

  • ...[10] çalışmasında, Weber yüzlerin özgün benzerlik gösterimi (self similarity representation of Weber face) önerilmektedir....

    [...]

Journal ArticleDOI
TL;DR: A system for facial kinship verification based on several kinds of texture descriptors with pyramid multilevel (PML) face representation for feature extraction along with paired feature representation and the authors' proposed robust feature selection to reduce the number of features is presented.
Abstract: We address kinship verification, which is a challenging problem in computer vision and pattern discovery. It has several applications, such as organizing photoalbums, recognizing resemblances among humans, and finding missing children. We present a system for facial kinship verification based on several kinds of texture descriptors (local binary patterns, local ternary patterns, local directional patterns, local phase quantization, and binarized statistical image features) with pyramid multilevel (PML) face representation for feature extraction along with our proposed paired feature representation and our proposed robust feature selection to reduce the number of features. The proposed approach consists of the following three main stages: (1) face preprocessing, (2) feature extraction and selection, and (3) kinship verification. Extensive experiments are conducted on five publicly available databases (Cornell, UB KinFace, Family 101, KinFace W-I, and KinFace W-II). Additionally, we provided a wide experiment for each stage to find the best and most suitable settings. We present many comparisons with state-of-the-art methods and through these comparisons, it appears that our experiments show stable and good results.

1 citations


Additional excerpts

  • ...EQ-TARGET;temp:intralink-;e004;116;216 S 0ðmc;mn; tÞ 1⁄4 8< : 1; mn > mc þ t 0; mn > mc − t and mn < mc þ t −1; mn < mc − t ; (4)...

    [...]

Journal Article
TL;DR: System first detects all the faces from given photo then extracts the features from the faces using Gabor wavelet transform, which ultimately results to the classification of whether kinship or not.
Abstract: There are many social networking web sites used by people and every day numbers of photos are uploaded by them on it. But from a photo we cannot predict the relationship among the people in photo. So there is a need for automatically identifying and predicting relationship, specifically kinship from photo. Proposed system comes under Computer Vision and is based on Face recognition, Feature extraction and knowledge transfer learning. System first detects all the faces from given photo then extracts the features from the faces using Gabor wavelet transform. A UB KinFace version 2.o database is used to train the system giving extracted features as a matrix that is compared with extracted features from photo, which ultimately results to the classification of whether kinship or not.

1 citations

Proceedings ArticleDOI
01 Jul 2017
TL;DR: A new video face dataset called Kinship Face Videos in the Wild (KFVW) is presented which were captured in wild conditions for the video-based kinship verification study, as well as the standard benchmark.
Abstract: In this paper, we investigate the problem of video-based kinship verification using discriminative metric learning. While several attempts have been made on facial kinship verification from still images, to our knowledge, the problem of video-based kinship verification has not been formally addressed in the literature. In this paper, we make the two contributions to video-based kinship verification. On one hand, we present a new video face dataset called Kinship Face Videos in the Wild (KFVW) which were captured in wild conditions for the video-based kinship verification study, as well as the standard benchmark. On the other hand, we employ two widely used metric learning methods for video-based kinship verification. Experimental results are presented to demonstrate the efficacy of our proposed dataset and the effectiveness of existing metric learning methods.

Cites background or methods from "Self-similarity representation of W..."

  • ..., Cor­ nellKin [5], VB KinFace [7], IIITD Kinship [18], Fam­ ily101 [12], KinFaceW-I [13], KinFaceW-II [13], TSKin­ Face [35], etc....

    [...]

  • ...[18] Local feature representation image 2012 Somanath el at....

    [...]

  • ...Representative such fea­ ture information include skin color [5], histogram of gradien­ t [5, 6, 11], Gabor wavelet [7, 10, 11, 23], gradient orientation pyramid [10], local binary pattern [13], scale-invariant feature transform [11, 13, 15], salient part [8, 9], self-similarity [18], and dynamic features combined with spatio-temporal appear­ ance descriptor [19]....

    [...]

  • ...While these methods have achieved some encouraging performance [5-13, 15, 18], it is still challenging to develop discriminative and robust kinship verification approaches for real-world applications, especially when face images are captured in unconstrained environments where large variations of pose, illumination, expression, and background occur....

    [...]

  • ...UB KinFace [7] lIITD Kinship [18] Family101 [12] KinFaceW-I [13] KinFaceW-I [13] TSKinFace [35] KFV W (Ours)...

    [...]

References
More filters
Proceedings ArticleDOI
20 Jun 2005
TL;DR: It is shown experimentally that grids of histograms of oriented gradient (HOG) descriptors significantly outperform existing feature sets for human detection, and the influence of each stage of the computation on performance is studied.
Abstract: We study the question of feature sets for robust visual object recognition; adopting linear SVM based human detection as a test case. After reviewing existing edge and gradient based descriptors, we show experimentally that grids of histograms of oriented gradient (HOG) descriptors significantly outperform existing feature sets for human detection. We study the influence of each stage of the computation on performance, concluding that fine-scale gradients, fine orientation binning, relatively coarse spatial binning, and high-quality local contrast normalization in overlapping descriptor blocks are all important for good results. The new approach gives near-perfect separation on the original MIT pedestrian database, so we introduce a more challenging dataset containing over 1800 annotated human images with a large range of pose variations and backgrounds.

31,952 citations


"Self-similarity representation of W..." refers background in this paper

  • ...75% which was comparatively better than Local Binary Pattern (LBP) [1], Histogram of Gradients (HOG) [4], Principal Component Analysis (PCA) [8], and Linear Embedding (LE) [2]....

    [...]

  • ...The authors reported an accuracy of 67.75% which was comparatively better than Local Binary Pattern (LBP) [1], Histogram of Gradients (HOG) [4], Principal Component Analysis (PCA) [8], and Linear Embedding (LE) [2]....

    [...]

01 Jan 1998
TL;DR: Presenting a method for determining the necessary and sufficient conditions for consistency of learning process, the author covers function estimates from small data pools, applying these estimations to real-life problems, and much more.
Abstract: A comprehensive look at learning and generalization theory. The statistical theory of learning and generalization concerns the problem of choosing desired functions on the basis of empirical data. Highly applicable to a variety of computer science and robotics fields, this book offers lucid coverage of the theory as a whole. Presenting a method for determining the necessary and sufficient conditions for consistency of learning process, the author covers function estimates from small data pools, applying these estimations to real-life problems, and much more.

26,531 citations


"Self-similarity representation of W..." refers methods in this paper

  • ...The χ(2) distance measures (in a vector form) are provided as input to the SVM classifier [11] with the classes being kin and non-kin....

    [...]

Proceedings ArticleDOI
01 Dec 2001
TL;DR: A machine learning approach for visual object detection which is capable of processing images extremely rapidly and achieving high detection rates and the introduction of a new image representation called the "integral image" which allows the features used by the detector to be computed very quickly.
Abstract: This paper describes a machine learning approach for visual object detection which is capable of processing images extremely rapidly and achieving high detection rates. This work is distinguished by three key contributions. The first is the introduction of a new image representation called the "integral image" which allows the features used by our detector to be computed very quickly. The second is a learning algorithm, based on AdaBoost, which selects a small number of critical visual features from a larger set and yields extremely efficient classifiers. The third contribution is a method for combining increasingly more complex classifiers in a "cascade" which allows background regions of the image to be quickly discarded while spending more computation on promising object-like regions. The cascade can be viewed as an object specific focus-of-attention mechanism which unlike previous approaches provides statistical guarantees that discarded regions are unlikely to contain the object of interest. In the domain of face detection the system yields detection rates comparable to the best previous systems. Used in real-time applications, the detector runs at 15 frames per second without resorting to image differencing or skin color detection.

18,620 citations


"Self-similarity representation of W..." refers methods in this paper

  • ...The face region present in the image is first extracted using the Adaboost face detector [12]....

    [...]

Book
03 Oct 1988
TL;DR: This chapter discusses two Dimensional Systems and Mathematical Preliminaries and their applications in Image Analysis and Computer Vision, as well as image reconstruction from Projections and image enhancement.
Abstract: Introduction. 1. Two Dimensional Systems and Mathematical Preliminaries. 2. Image Perception. 3. Image Sampling and Quantization. 4. Image Transforms. 5. Image Representation by Stochastic Models. 6. Image Enhancement. 7. Image Filtering and Restoration. 8. Image Analysis and Computer Vision. 9. Image Reconstruction From Projections. 10. Image Data Compression.

8,504 citations


"Self-similarity representation of W..." refers methods in this paper

  • ...Therefore, Difference of Gaussian (DoG) approach [7] has been applied to extract these features using the steps below....

    [...]

Journal ArticleDOI
TL;DR: This paper presents a novel and efficient facial image representation based on local binary pattern (LBP) texture features that is assessed in the face recognition problem under different challenges.
Abstract: This paper presents a novel and efficient facial image representation based on local binary pattern (LBP) texture features. The face image is divided into several regions from which the LBP feature distributions are extracted and concatenated into an enhanced feature vector to be used as a face descriptor. The performance of the proposed method is assessed in the face recognition problem under different challenges. Other applications and several extensions are also discussed

5,563 citations


"Self-similarity representation of W..." refers background in this paper

  • ...75% which was comparatively better than Local Binary Pattern (LBP) [1], Histogram of Gradients (HOG) [4], Principal Component Analysis (PCA) [8], and Linear Embedding (LE) [2]....

    [...]

  • ...The authors reported an accuracy of 67.75% which was comparatively better than Local Binary Pattern (LBP) [1], Histogram of Gradients (HOG) [4], Principal Component Analysis (PCA) [8], and Linear Embedding (LE) [2]....

    [...]