Face Detection using Local SMQT Features and Split up Snow Classifier

Nilsson, Mikael; Nordberg, Jörgen; Claesson, Ingvar

doi:10.1109/icassp.2007.366304

Cited by 109 publications

(80 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We have used an existing method for face detection using the illumination insensitive features gained from the local Successive Mean Quantization Transform (SMQT) features and split up Sparse Network of Winnows (SNoW) classifier wich achive rapid detection. (Nilsson et al, 2007) …”

Section: Face Detectionmentioning

confidence: 99%

Fast MicroSleep and Yawning Detections to Assess Driver’s Vigilance Level

Alioua

Amine

Rziza

et al. 2011

Proceedings of the 6th International Driving Symposium on Human Factors in Driver Assessment, Training, and Vehicle Design : Dr

View full text Add to dashboard Cite

Summary: Driver hypovigilance, often caused by fatigue and/or drowsiness, receives increasing attention in the last years; especially after it became evident that hypovigilance is a one of the major factor causing traffic accidents. Monitoring and detecting driver hypovigilance could contribute significantly to improve road traffic safety. This paper proposes fast methods to identify drowsiness and fatigue using respectively microsleep and yawning detections. In this study, the proposed scheme begins by a face detection using local Successive Mean Quantization Transform (SMQT) features and split up Sparse Network of Winnows (SNoW) classifier. After performing face detection, the novel approach for eye/mouth detection, based on Circular Hough Transform (CHT), is applied on eyes and mouth extracted regions. Our proposed methods works in real-time and yield a high detection rates whether for drowsiness or fatigue detections.

show abstract

Section: Face Detectionmentioning

confidence: 99%

Fast MicroSleep and Yawning Detections to Assess Driver’s Vigilance Level

Alioua

Amine

Rziza

et al. 2011

Proceedings of the 6th International Driving Symposium on Human Factors in Driver Assessment, Training, and Vehicle Design : Dr

View full text Add to dashboard Cite

show abstract

“…Hence, rapid detection is the main concern. Using features that can be computed fast and have desirable properties with regard to illumination changes, such as Local Binary Patterns (LBP) (Ojala et al, 1994) or local Successive Mean Quantization Transform (SMQT) (Nilsson et al, 2005;Nilsson et al, 2007), are therefore of great interest. Both consist of binary patterns formed by comparing pixels within 3 × 3 patches.…”

Section: Bicycle Detection Using Classifier Cascadementioning

confidence: 99%

“…An efficient classifier cascade based on the split up SNoW (Nilsson et al, 2007), which produces a cascade, is employed in this paper. It should be noted that the following search space discussion could be equally valid if another object detector, using similar a scanning windows approach, is used (Viola and Jones, 2001;Dalal and Triggs, 2005;Zhang et al, 2007;Felzenszwalb et al, 2010).…”

Section: Bicycle Detection Using Classifier Cascadementioning

confidence: 99%

See 1 more Smart Citation

Reduced Search Space for Rapid Bicycle Detection

Ardö

Nilsson

Laureshyn³

et al. 2013

Proceedings of the 2nd International Conference on Pattern Recognition Applications and Methods

View full text Add to dashboard Cite

Abstract:This paper describes a solution to the application of rapid detection of bicycles in low resolution video. In particular, the application addressed is from video recorded in a live environment. The future aim from the results in this paper is to investigate a full year of video data. Hence, processing speed is of great concern.The proposed solution involves the use of an object detector and a search space reduction method based on prior knowledge regarding the application at hand. The method using prior knowledge utilizes random sample consensus, and additional statistical analysis on detection outputs, in order to define a reduced search space. It is experimentally shown that, in the application addressed, it is possible to reduce the full search space by 62% with the proposed methodology. This approach, which employs a full detector in combination with the design of a simple and fast model that can capture prior knowledge for a specific application, leads to a reduced search space and thereby a significantly improved processing speed.

show abstract

“…Nilsson et al [15] information (i.e., depth image that represents the distance between a camera and objects) is also used to reliably perform face detection. Kosov et al [16] proposed a depth map based face detection algorithm using principal component analysis (PCA), where the depth map is generated from captured stereo images.…”

Section: Introductionmentioning

confidence: 99%

Face Detection Using Adaboost and Template Matching of Depth Map based Block Rank Patterns

Kim¹,

Park²,

Mun³

2012

Journal of Broadcast Engineering

View full text Add to dashboard Cite

성능을 Kinect sensor로 취득한 실제 영상으로 실험하였다. 실험 결과 true positive를 잘 보존하면서 많은 false positive들을 효과적으 로 제거하는 것을 보여준다. AbstractA face detection algorithms using two-dimensional (2-D) intensity or color images have been studied for decades. Recently, with the development of low-cost range sensor, three-dimensional (3-D) information (i.e., depth image that represents the distance between a camera and objects) can be easily used to reliably extract facial features. Most people have a similar pattern of 3-D facial structure. This paper proposes a face detection method using intensity and depth images. At first, adaboost algorithm using intensity image classifies face and nonface candidate regions. Each candidate region is divided into 5×5 blocks and depth values are averaged in each block. Then, 5×5 block rank pattern is constructed by sorting block averages of depth values. Finally, candidate regions are classified as face and nonface regions by matching the constructed depth map based block rank patterns and a template pattern that is generated from training data set. For template matching, the 5×5 template block rank pattern is prior constructed by averaging block ranks using training data set. The proposed algorithm is tested on real images obtained by Kinect range sensor. Experimental results show that the proposed algorithm effectively eliminates most false positives with true positives well preserved. Other face detection approach is template matching, in which the template (constructed from training set) and a pattern of candidate region (detected from input image) are compared to classify face and nonface. Various algorithms using template matching have been studied. Predefined fixed-size windows were used as templates to detect facial features [6]. Then, the template matching algorithm using variable size window that can detect faces of varying sizes was presented [7]. To construct a template of accurate face region, Kherchaoui and Houacine [8] proposed a template matching algorithm using a model of skin color with constraints. Template matching algorithms using skin information and lines of face template was also presented [9].Liu et al. [10] proposed a template matching algorithm using radial template to detect rotated face in any orientation.Jeng et al. [11] proposed a template matching algorithm using a geometrical face model using relative distance be- Finally, each candidate region is classified as a face and nonface region by matching the constructed depth map based block rank patterns and a template that is generated from training data set. For template matching, the 5×5 template block rank pattern is a priori constructed by averaging block ranks of training data set. To obtain training and test data set, we use Kinect range sensor [21]. Infrared projector projects infrared patterns that people cannot see.Infrared image is obtained by infrared camera and used to generate depth map. However, the regions that are not projected by occlusion have no depth data.The rest of the paper is structured as follows. Sec...

show abstract

Face Detection using Local SMQT Features and Split up Snow Classifier

Cited by 109 publications

References 9 publications

Fast MicroSleep and Yawning Detections to Assess Driver’s Vigilance Level

Fast MicroSleep and Yawning Detections to Assess Driver’s Vigilance Level

Reduced Search Space for Rapid Bicycle Detection

Face Detection Using Adaboost and Template Matching of Depth Map based Block Rank Patterns

Contact Info

Product

Resources

About