A pseudo-distance measure for 2D shapes based on turning angle

Niblack, W.; Yin, Jichong

doi:10.1109/icip.1995.537646

Cited by 29 publications

(12 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Our algorithm extends existing template matching algorithms [KZ04,WAWL07,NY95,AB10]. We investigated two popular features, Euclidean distance [KZ04,WAWL07] and turning angle [NY95,AB10]. We found that the turning angle measure consistently resulted in higher accuracy than Euclidean distance (see Table 1).…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Continuous recognition and visualization of pen strokes and touch-screen gestures

Kristensson

Denby

2011

Proceedings of the Eighth Eurographics Symposium on Sketch-Based Interfaces and Modeling

View full text Add to dashboard Cite

We present a technique that enables continuous recognition and visualization of pen strokes and touch-screen gestures. We describe an incremental recognition algorithm that provides probability distributions over template classes as a function of users' partial or complete stroke articulations. We show that this algorithm can predict users' intended template classes with high accuracy on several different datasets. We use the algorithm to design two new visualizations that reveal various aspects of the recognition process to users. We then demonstrate how these visualizations can help users to understand how the recognition process interprets their input and how interactions between different template classes affect recognition outcomes.

show abstract

Section: Discussionmentioning

confidence: 99%

“…This similarity measure was originally proposed by Niblack and Yin [NY95] for image-lookup databases and was later used by Appert and Bau [AB10] to predict the scale of gestures for the command selection technique Octopocus [BM08].…”

Section: Similarity Measuresmentioning

confidence: 99%

Continuous recognition and visualization of pen strokes and touch-screen gestures

Kristensson

Denby

2011

Proceedings of the Eighth Eurographics Symposium on Sketch-Based Interfaces and Modeling

View full text Add to dashboard Cite

show abstract

“…The proposed algorithm initially segments the image (see fig.4), by thresholding the saliency map, as discussed for the Image Cropping service, and refines the segmentation by using active contours [6]. It then extracts features from the foreground of the scene: texture (Edge Histogram [7]), color (Color Histogram) and shape (Turning Angle [8] Histogram). These descriptors are used to train three separate SVM classifiers, and the image is classified as weapon by majority.…”

Section: Weapon Detectionmentioning

confidence: 99%

Toward an Integrated System for Surveillance and Behaviour Analysis of Groups and People

Ardizzone

Bruno

Gallea

et al. 2013

New Trends in Image Analysis and Processing – ICIAP 2013

View full text Add to dashboard Cite

Abstract. Security and INTelligence SYStem is an Italian research project which aims to create an integrated system for the analysis of multi-modal data sources (text, images, video, audio), to assist operators in homeland security applications. Within this project the Scientific Research Unit of the University of Palermo is responsible of the image and video analysis activity. The SRU of Palermo developed a web service based architecture that provides image and video analysis capabilities to the integrated analysis system. The developed architecture uses both state of the art techniques, adapted to cope with the particular problem at hand, and new algorithms to provide the following services: image cropping, image forgery detection, face and people detection, weapon detection and classification, and terrorist logo recognition. In the last phase of the project we plan to include in our system new services, mainly oriented to the video analysis, to study and understand the behaviour of individuals, either alone or in a group.

show abstract

“…We were inspired by the "turning angles representation" algorithm used in image analysis [8]. It represents a shape as a vector of turning angles.…”

Section: Incomplete Input Scale Estimationmentioning

confidence: 99%

Scale detection for a priori gesture recognition

Appert

Bau

2010

Proceedings of the SIGCHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

Gesture-based interfaces provide expert users with an efficient form of interaction but they require a learning effort for novice users. To address this problem, some on-line guiding techniques display all available gestures in response to partial input. However, partial input recognition algorithms are scale dependent while most gesture recognizers support scale independence (i.e., the same shape at different scales actually invokes the same command). We propose an algorithm for estimating the scale of any partial input in the context of a gesture recognition system and illustrate how it can be used to improve users' experience with gesture-based systems.

show abstract

A pseudo-distance measure for 2D shapes based on turning angle

Cited by 29 publications

References 9 publications

Continuous recognition and visualization of pen strokes and touch-screen gestures

Continuous recognition and visualization of pen strokes and touch-screen gestures

Toward an Integrated System for Surveillance and Behaviour Analysis of Groups and People

Scale detection for a priori gesture recognition

Contact Info

Product

Resources

About