Human Computer Interaction Using Hand Gestures

verfasst von: Prashan Premaratne

Verlag: Springer Singapore

Buchreihe : Cognitive Science and Technology

Enthalten in: Springer Professional "Wirtschaft+Technik" , Springer Professional "Technik" , Springer Professional "Wirtschaft"

Einloggen, um Zugang zu erhalten

Über dieses Buch

Human computer interaction (HCI) plays a vital role in bridging the 'Digital Divide', bringing people closer to consumer electronics control in the 'lounge'. Keyboards and mouse or remotes do alienate old and new generations alike from control interfaces. Hand Gesture Recognition systems bring hope of connecting people with machines in a natural way. This will lead to consumers being able to use their hands naturally to communicate with any electronic equipment in their 'lounge.' This monograph will include the state of the art hand gesture recognition approaches and how they evolved from their inception. The author would also detail his research in this area for the past 8 years and how the future might turn out to be using HCI. This monograph will serve as a valuable guide for researchers (who would endeavour into) in the world of HCI.

Inhaltsverzeichnis

Frontmatter

1. Introduction

Abstract

The first human interaction with a computer goes back to the days when punch cards were used to program computers. Then the output of the computers was also punched holes on cards. This was a very slow way of communication and the interaction was totally different to what we have today.

Prashan Premaratne

2. Historical Development of Hand Gesture Recognition

Abstract

The history of hand gesture recognition for computer control started with the invention of glove-based control interfaces. Researchers realized that gestures inspired by sign language can be used to offer simple commands for a computer interface. This gradually evolved with the development of much accurate accelerometers, infrared cameras and even fibreoptic bend-sensors (optical goniometers). Some of those developments in glove based systems eventually offered the ability to realize computer vision based recognition without any sensors attached to the glove. These are the coloured gloves or gloves that offer unique colours for finger tracking ability that would be discussed here on computer vision based gesture recognition. Over past 25 years, this evolution has resulted in many successful products that offer total wireless connection with least resistance to the wearer and will be discussed in Chap. 7. This chapter discusses the chronological order of some fundamental approaches that significantly contributed to the expansion of the knowledge of hand gesture recognition.

Prashan Premaratne

3. Pre-processing

Abstract

Computer vision is aimed at simulating the human visual system in order to extract useful information for machines to make decisions. A visual camera is usually used for this purpose which detects brightness, colour, texture and dimensions of an object in focus. When a camera captures scenery, it contains both ‘wanted’ as well as ‘unwanted’ information. If the camera is focussed on a person’s hand looking for a possible gesture, then the ‘unwanted’ objects in the scenery would be the background which may contain the person’s body, clothing, other people, pets, walls, windows, curtains or any other equipment. Since the system is developed to respond to gestures, the system would try to extract only the ‘wanted’ information. However, as the system would not have the level of intelligence as a human, it relies on ‘clues’ to extract only the ‘wanted’ objects.

Prashan Premaratne

4. Feature Extraction

Abstract

An image is worth 1,000 words. Yet, a machine to describe a picture or a color image is not trivial. Of course, some measurements can easily be estimated such as different colors, their intensities, size and dimensions of certain objects if the object can be specified. Yet, the most difficult aspect is to make the decisions as to what constitute an object. In a scene consisting of hand gesture or gestures and a cluttered background, difficulty lies in interpreting these items. Perhaps, the hand gesture recognition offers some help compared to other problems as skin detection can be used to define a hand as was discussed under Pre-processing in Chap. 3. Yet, even when a hand is detected and isolated, what configuration the hand shows is again a difficult question to address.

Prashan Premaratne

5. Effective Hand Gesture Classification Approaches

Abstract

Hand gestures recognition goals can only be fulfilled when gesture isolation is coupled with an effective feature extraction followed by highly efficient classification. In the context of machine vision, feature extraction and classification can be jointly called pattern recognition in which, previous known patterns are matched with a query gesture.

Prashan Premaratne

6. Sign Languages of the World

Abstract

Sign languages have been there since the start of the humanity and would have been the first means of communication among the primitive humans. Before people communicated with a vocabulary and using sounds, it is fair to assume that they communicated with various gestures using hand, face, mouth and body movements. However, today, the sign language is predominantly associated with disabilities from congenital to accidents. Most of the users are either hearing impaired or mute. There is also a subgroup of whom are children of such hearing impaired people whose senses are not affected but do use sign language because of the community needs in which they live.

Prashan Premaratne

7. Future Trends in Hand Gesture Recognition

Abstract

In 2005, the author developed a comprehensive hand gesture recognition system that was capable of controlling many consumer electronics control devices. The publicity around this development was echoed in 2007 after the publication of this research in IET Computer Vision journal (Premaratne and Nguyen, IET Comput. Vision. 1, 35–41 (2007)). The media frenzy that was generated around the world due to this invention was unprecedented. He was contacted by Microsoft Australia, Logitech USA and NDA the world’s largest settop box manufacturer to discuss future trends emanating from the development. Six months later, Samsung patented similar technology for their mobile phones. By 2009, Toshiba and Samsung developed digital Television with a built-in hand gesture interface. In 2013, there were 20 consumer electronics devices with gesture control were added to the gadgets world.

Prashan Premaratne

Titel: Human Computer Interaction Using Hand Gestures
verfasst von: Prashan Premaratne
Verlag: Springer Singapore
Electronic ISBN: 978-981-4585-69-9
Print ISBN: 978-981-4585-68-2
DOI: https://doi.org/10.1007/978-981-4585-69-9