Stream processing for fast and efficient rotated Haar-like features using rotated integral images

Messom, Chris; Barczak, Andre L. C.

doi:10.1504/ijista.2009.025105

Cited by 29 publications

(20 citation statements)

References 27 publications

(4 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Given the spatial discretization of digital images, we use discrete unit-integer orientations (see Figure 2) as termed by Messom et al [18]. A unit-integer orientation is an orientation α = arctan(b/a) defined by horizontal and vertical offset components a and b, such that both components are integers and at least one of them is 1 or -1.…”

Section: Shape-based Detectionmentioning

confidence: 99%

Pedestrian detection using GPU-accelerated multiple cue computation

Beleznai

Schreiber

Rauter

2011

CVPR 2011 Workshops

View full text Add to dashboard Cite

Achieving accurate pedestrian detection for practically relevant scenarios in real-time is an important problem for many applications, while representing a major scientific challenge at the same time. In this paper we present an algorithmic framework which efficiently computes pedestrian-specific shape and motion cues and combines them in a probabilistic manner to infer the location and occlusion status of pedestrians viewed by a stationary camera. The articulated pedestrian shape is represented by a set of sparse contour templates, where fast template matching against image features is carried out using integral images built along oriented scan-lines. The motion cue is obtained by employing a non-parametric background model using the YCbCr color space. Both cues are computed and evaluated on the GPU. Given the probabilistic output from the two cues the spatial configuration of hypothesized human body locations is obtained by an iterative optimization scheme taking into account the depth ordering and occlusion status of individual hypotheses. The method achieves fast computation times even in complex scenarios with a high pedestrian density. Employed computational schemes are described in detail and the validity of the approach is demonstrated on three PETS2009 datasets depicting increasing pedestrian density. Evaluation results and comparison with state of the art are presented.

show abstract

Section: Shape-based Detectionmentioning

confidence: 99%

Pedestrian detection using GPU-accelerated multiple cue computation

Beleznai

Schreiber

Rauter

2011

CVPR 2011 Workshops

View full text Add to dashboard Cite

show abstract

“…It uses greyscale differences between rectangles to extract object features [1]. Haar-like features are calculated by subtracting the sum of a sub-window of the feature from the sum of the remaining window of the feature [27]. Lienhart and Maydt [4] added rotated features, significantly enhancing the learning system and improving the classifier performance.…”

Section: Haar Cascade Classifier (Hcc) Approachmentioning

confidence: 99%

Arabic character recognition using a Haar cascade classifier approach (HCC)

AbdelRaouf

Higgins

Pridmore

et al. 2015

Pattern Anal Applic

View full text Add to dashboard Cite

Optical character recognition (OCR) shows great potential for rapid data entry, but has limited success when applied to the Arabic language. Traditional OCR problems are compounded by the nature of Arabic language and because the script is heavily connected. A machine learning, Haar cascade classifier (HCC) approach was introduced by Viola and Jones (Rapid object detection using a boosted cascade of simple features. Kauai, Hawaii, 2001) to achieve rapid object detection based on a boosted cascade of simple Haar-like features. Here, that approach is applied for the first time to suit Arabic glyph recognition. HCC approach eliminates problematic steps in the preprocessing and recognition phases and, most importantly, character segmentation stage. A classifier was produced for each of the 61 Arabic glyphs that exist after the removal of diacritical marks (dots). These classifiers were trained and tested on some 2,000 images each. The system was tested with real text images and produces a recognition rate for Arabic glyphs of 87 %. The technique gives good results relative to those achieved using a commercial Arabic OCR application and existing state-of-the-art research application.

show abstract

“…Figure 4. T he concept of Integral Image [17] Each obtained frame is subtracted with the background to get the newly entered object in the scene. Entire frame is divided into 2 gray levels in which hand is given the highest gray level value while other is given near 0 by using average filter.…”

Section: B Image Preprocessingmentioning

confidence: 99%

Real Time Multiple Hand Gesture Recognition System for Human Computer Interaction

Rautaray¹,

Agrawal²

2012

IJISA

View full text Add to dashboard Cite

Abstract-With the increasing use of computing devices in day to day life, the need of user friendly interfaces has lead towards the evolution of different types of interfaces for human co mputer interaction. Real t ime vision based hand gesture recognition affords users the ability to interact with computers in more natural and intuitive ways. Direct use of hands as an input device is an attractive method which can co mmunicate much more information by itself in comparison to mice, joysticks etc allowing a greater nu mber of recognition system that can be used in a variety of human computer interaction applicat ions. The gesture recognition system consist of three main modules like hand segmentation, hand tracking and gesture recognition fro m hand features. The designed system further integrated with different applications like image bro wser, virtual game etc. possibilities for hu man computer interaction. Co mputer Vision based systems has the potential to provide more natural, non-contact solutions. The present research work focuses on to design and develops a practical framework for real time hand gesture Index Terms-Real t ime, gesture recognition, human computer interaction, tracking. I. INTRO DUCTIO NSince their first appearance, co mputers have become a key element of our society. Surfing the web, typing a letter, playing a video game or storing and retriev ing data are just a few o f the examp les involving the use of computers. And due to the constant decrease in price of personal computers, they will even more influence our everyday life in the near future.To efficiently use them, most computer applications require more and more interaction. Fo r that reason, human-computer interaction (HCI) has been a lively field of research these las t few years. Firstly based in the past on punched cards, reserved to experts, the interaction has evolved to the graphical interface paradigm. The interaction consists of the direct man ipulation of graphic objects such as icons and windows using a pointing device. Even if the invention of keyboard and mouse is a great progress, there are still situations in wh ich these devices can be seen as dinosaurs of HCI. This is particularly the case for the interaction with 3D objects. The 2 degrees of freedo m (DOFs) of the mouse cannot properly emulate the 3 dimensions of space. Furthermore, such interfaces are often not intuitive to use. To achieve natural and immersive hu man-co mputer interaction, the hu man hand could be used as an interface device [1]. Hand gestures are a powerfu l hu man to-hu man co mmunication channel, which forms a major part of information transfer in our everyday life. Hand gestures are an easy to use and natural way of interaction. Using hands as a device can help people co mmunicate with computers in a more intuitive and natural way. When we interact with other people, our hand movements play an important role and the information they convey is very rich in many ways. We use our hands for pointing at a person or at an object, conveying informati...

show abstract

Stream processing for fast and efficient rotated Haar-like features using rotated integral images

Cited by 29 publications

References 27 publications

Pedestrian detection using GPU-accelerated multiple cue computation

Pedestrian detection using GPU-accelerated multiple cue computation

Arabic character recognition using a Haar cascade classifier approach (HCC)

Real Time Multiple Hand Gesture Recognition System for Human Computer Interaction

Contact Info

Product

Resources

About