PicoLife: A Computer Vision-based Gesture Recognition and 3D Gaming System for Android Mobile Devices

The field of hand gesture recognition has recently reached new heights thanks to its widespread use in domains like remote sensing, robotic control, and smart home appliances, among others. Despite this, identifying gestures is difficult because of the intransigent features of the human hand, which make the codes used to decode them illegible and impossible to compare. Differentiating regional patterns is the job of pattern recognition. Pattern recognition is at the heart of sign language. People who are deaf or mute may understand the spoken language of the rest of the world by learning sign language. Any part of the body may be used to create signs in sign language. The suggested system employs a gesture recognition system trained on Indian sign language. The methods of preprocessing, hand segmentation, feature extraction, gesture identification, and classification of hand gestures are discussed in this work as they pertain to hand gesture sign language. A hybrid approach is used to extract the features, which combines the usage of Haar-like features with the application of Histogram of Oriented Gradients (HOG).The SVM classifier is then fed the characteristics it has extracted from the pictures in order to make an accurate classification. A false rejection error rate of 8% is achieved while the accuracy of hand gesture detection is improved by 93.5%.

show abstract

“…An appropriate, effective, and user-friendly interface is provided through the use of virtually controlled hand movement. [20]…”

Section: B Regulating Playmentioning

confidence: 99%

Analysis of the Efficacy of Real-Time Hand Gesture Detection with Hog and Haar-Like Features Using SVM Classification

Theresa¹,

Prabha²,

Thilagavathy³

et al. 2022

IJRITCC

View full text Add to dashboard Cite

show abstract

“…Li et al created a backlight system, using a backlit table to project hands towards a camera where the shapes of hands would be marked dark in the white camera space [6]; however, hand movements are limited to the size of the table and to a particular angle of interactions. Mariappan et al used infrared markers worn by subjects to capture human movements, achieving good quality of computer mapping results but requiring markers [7]. Bernardes et al [1] used a color based system without markers on the user to establish gesture-based controls, but the mapping result is not always accurate due to unstable illuminations or the problems of image capture.…”

Section: Background and Related Workmentioning

confidence: 99%

Empirically measuring control quality of gesture input

Chastine

Franklin

Peng

et al. 2014

2014 Computer Games: AI, Animation, Mobile, Multimedia, Educational and Serious Games (CGAMES)

View full text Add to dashboard Cite

As new input devices emerge new paradigms of interaction must emerge with them. Recent advances in technology have lowered the cost of gesture-based hardware, enabling them to be adopted by and integrated into mainstream applications. Given the novelty of these devices, however, little is known about how this form of interaction can be integrated into existing computing paradigms or how it compares with existing input methods. It is therefore important to examine the role of gesture control across current applications in various contexts. While gesture-based input is likely to yield a variety of novel interaction techniques for immersive 3D environments, it is important to understand how spatial controls map to 2D interfaces and how lessons learned in the 2D space map into these 3D environments.In this paper, we present the results of a study of using gesture alone to control a top-down shooter game using two novel techniques; interaction via a gamepad was used to establish a baseline of performance. We measured users' performance of basic tasks (moving and aiming), and then utilized a subjective post-study survey. The motivation of this study is not to directly compare the performance of the gamepad with gesture controls (given a time-on-task bias in favor of gamepad control), but rather to establish a baseline of expected user performance for those with no prior gesture-based experience. The contributions of this research include the design and evaluation of two new gesture-based techniques for 2D control and the presentation and analysis of our results.

show abstract