Components and Their Topology for Robust Face Detection in the Presence of Partial Occlusions

Goldmann, Lutz; Monich, Ullrich J.; Sikora, Thomas

doi:10.1109/tifs.2007.902019

Cited by 26 publications

(17 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Representative works regarding occlusion include those of Hotta [9], who introduced an SVM face detector that used multiple kernels computed over a variety of image regions; Lin et al [20], who proposed a multi-class variation of AdaBoost and used it to decompose the face class into region-based occlusion categories; and Goldmann et al [6], who approached the occlusion problem by detecting four face parts independently. Blur has received even less attention from the face detection community.…”

Section: Discussionmentioning

confidence: 99%

The effectiveness of face detection algorithms in unconstrained crowd scenes

Barr

Bowyer

Flynn

2014

IEEE Winter Conference on Applications of Computer Vision

View full text Add to dashboard Cite

show abstract

Section: Discussionmentioning

confidence: 99%

The effectiveness of face detection algorithms in unconstrained crowd scenes

Barr

Bowyer

Flynn

2014

IEEE Winter Conference on Applications of Computer Vision

View full text Add to dashboard Cite

show abstract

“…The l 1 is the length of the left eye and l 2 is the length of the right eye. (6) If the evaluation of the equation (4) is larger than the threshold value 0.8, these two feature blocks are considered as eye features. The relative region in the geometrical model is searched for other facial candidates.…”

Section: Geometrical Facial Feature Extraction With Belief Propagationmentioning

confidence: 99%

“…P F Felzenszwalb and Huttenlocher D P [5] presented a computationally efficient frame work for part based modeling and recognition of objects. Lutz Goldman Ullrich J M and Thomas Sikora [6] proposed component detection based on haar like feature with adaboost classifier and topology verification is based on graph matching technique. (iii) Image parsing approaches were introduced in the last 5 years for object segmentation, detection and recognition.…”

Section: Introductionmentioning

confidence: 99%

Probabilistic Parser for Face Detection

2009

View full text Add to dashboard Cite

Abstract-In this paper, we have proposed probabilistic parser for identifying the face in a given scene image. Many object detection techniques use pattern statistical methods for feature extraction which is resource intensive and time consuming. We proposed a novel certainty factor based geometrical formulation for facial feature extraction. The proposed method accurately detects the facial components like eyes, nose and mouth in the presence of complex background. In the next stage, the AND/OR graph based recursive Top-down/Bottom-up image parser is used to detect the face in the input image by using the detected facial components. The image parser grammar represents both the decomposition of the scene image and the context for spatial relation by horizontal link between the vertices of the graph. The AND/OR graph is used to represent compositional structure of the image. The AND node represents the decomposition of the visual object into number of components and OR node represents the alternative sub-configuration /component. The experimental result confirms that our method outperforms some of the existing face detection methods.

show abstract

“…In the current system the component based approach by Goldmann et al [5] has been adopted. It has been shown that this approach can not only detect partially occluded faces, but also localizes these occlusions.…”

Section: B Video Analysismentioning

confidence: 99%

Multimodal person search combining information fusion and relevance feedback

Goldmann

Samour

Ebrahimi

et al. 2009

2009 IEEE International Workshop on Multimedia Signal Processing

Self Cite

View full text Add to dashboard Cite

Abstract-With the increasing amount of multimedia data, efficient tools for search and retrieval are needed. Since people are naturally one of the most interesting objects within these documents, a system for multimodal person search and retrieval has been developed. It combines the audiovisual analysis of persons with the query by example paradigm and relevance feedback to provide an efficient tool for searching multimedia data. For the relevance feedback, one and two class approaches are considered and compared to each other. Multimodal fusion techniques are used to exploit the complementary character of the audio and video information. The experimental results prove that multimodal person search and retrieval is feasible and more efficient than manual exploration.

show abstract

Components and Their Topology for Robust Face Detection in the Presence of Partial Occlusions

Cited by 26 publications

References 11 publications

The effectiveness of face detection algorithms in unconstrained crowd scenes

The effectiveness of face detection algorithms in unconstrained crowd scenes

Probabilistic Parser for Face Detection

Multimodal person search combining information fusion and relevance feedback

Contact Info

Product

Resources

About