The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Penggunaan isyarat tangan menyediakan alternatif menarik kepada peranti antara muka yang menyusahkan untuk interaksi manusia-komputer (HCI). Khususnya, tafsiran visual gerak isyarat tangan boleh membantu mencapai pemahaman yang mudah dan semula jadi untuk HCI. Banyak kaedah untuk pengecaman isyarat tangan menggunakan analisis visual telah dicadangkan seperti analisis sintaksis, rangkaian saraf (NN), dan model Markov tersembunyi (HMM). Dalam penyelidikan kami, HMM dicadangkan untuk pengecaman isyarat tangan mengikut abjad. Dalam peringkat prapemprosesan, pendekatan yang dicadangkan terdiri daripada tiga prosedur berbeza untuk penyetempatan tangan, pengesanan tangan dan pengesanan isyarat. Prosedur lokasi tangan mengesan kawasan yang dicalonkan berdasarkan warna kulit dan gerakan dalam imej dengan menggunakan padanan histogram warna dan teknik perbezaan kelebihan masa. Algoritma penjejakan tangan mencari centroid bagi kawasan tangan yang bergerak, menyambungkan centroid tersebut dan menghasilkan trajektori. Algoritma pengesanan membahagikan trajektori kepada gerak isyarat yang nyata dan tidak bermakna. Dalam membina pangkalan data ciri, pendekatan yang dicadangkan menggunakan kod ciri ρ-φ-ν berwajaran, dan menggunakan k-bermaksud algoritma untuk buku kod HMM. Dalam percubaan kami, masing-masing 1,300 abjad dan 1,300 gerak isyarat tidak terlatih digunakan untuk latihan dan ujian. Keputusan eksperimen tersebut menunjukkan bahawa pendekatan yang dicadangkan menghasilkan kadar pengecaman yang lebih tinggi dan memuaskan untuk imej dengan saiz, bentuk dan sudut senget yang berbeza.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Salinan
Ho-Sub YOON, Jung SOH, Byung-Woo MIN, Hyun Seung YANG, "Recognition of Alphabetical Hand Gestures Using Hidden Markov Model" in IEICE TRANSACTIONS on Fundamentals,
vol. E82-A, no. 7, pp. 1358-1366, July 1999, doi: .
Abstract: The use of hand gesture provides an attractive alternative to cumbersome interface devices for human-computer interaction (HCI). In particular, visual interpretation of hand gestures can help achieve easy and natural comprehension for HCI. Many methods for hand gesture recognition using visual analysis have been proposed such as syntactical analysis, neural network (NN), and hidden Markov model (HMM)s. In our research, HMMs are proposed for alphabetical hand gesture recognition. In the preprocessing stage, the proposed approach consists of three different procedures for hand localization, hand tracking and gesture spotting. The hand location procedure detects the candidated regions on the basis of skin color and motion in an image by using a color histogram matching and time-varying edge difference techniques. The hand tracking algorithm finds the centroid of a moving hand region, connect those centroids, and produces a trajectory. The spotting algorithm divides the trajectory into real and meaningless gestures. In constructing a feature database, the proposed approach uses the weighted ρ-φ-ν feature code, and employ a k-means algorithm for the codebook of HMM. In our experiments, 1,300 alphabetical and 1,300 untrained gestures are used for training and testing, respectively. Those experimental results demonstrate that the proposed approach yields a higher and satisfactory recognition rate for the images with different sizes, shapes and skew angles.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/e82-a_7_1358/_p
Salinan
@ARTICLE{e82-a_7_1358,
author={Ho-Sub YOON, Jung SOH, Byung-Woo MIN, Hyun Seung YANG, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Recognition of Alphabetical Hand Gestures Using Hidden Markov Model},
year={1999},
volume={E82-A},
number={7},
pages={1358-1366},
abstract={The use of hand gesture provides an attractive alternative to cumbersome interface devices for human-computer interaction (HCI). In particular, visual interpretation of hand gestures can help achieve easy and natural comprehension for HCI. Many methods for hand gesture recognition using visual analysis have been proposed such as syntactical analysis, neural network (NN), and hidden Markov model (HMM)s. In our research, HMMs are proposed for alphabetical hand gesture recognition. In the preprocessing stage, the proposed approach consists of three different procedures for hand localization, hand tracking and gesture spotting. The hand location procedure detects the candidated regions on the basis of skin color and motion in an image by using a color histogram matching and time-varying edge difference techniques. The hand tracking algorithm finds the centroid of a moving hand region, connect those centroids, and produces a trajectory. The spotting algorithm divides the trajectory into real and meaningless gestures. In constructing a feature database, the proposed approach uses the weighted ρ-φ-ν feature code, and employ a k-means algorithm for the codebook of HMM. In our experiments, 1,300 alphabetical and 1,300 untrained gestures are used for training and testing, respectively. Those experimental results demonstrate that the proposed approach yields a higher and satisfactory recognition rate for the images with different sizes, shapes and skew angles.},
keywords={},
doi={},
ISSN={},
month={July},}
Salinan
TY - JOUR
TI - Recognition of Alphabetical Hand Gestures Using Hidden Markov Model
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1358
EP - 1366
AU - Ho-Sub YOON
AU - Jung SOH
AU - Byung-Woo MIN
AU - Hyun Seung YANG
PY - 1999
DO -
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E82-A
IS - 7
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - July 1999
AB - The use of hand gesture provides an attractive alternative to cumbersome interface devices for human-computer interaction (HCI). In particular, visual interpretation of hand gestures can help achieve easy and natural comprehension for HCI. Many methods for hand gesture recognition using visual analysis have been proposed such as syntactical analysis, neural network (NN), and hidden Markov model (HMM)s. In our research, HMMs are proposed for alphabetical hand gesture recognition. In the preprocessing stage, the proposed approach consists of three different procedures for hand localization, hand tracking and gesture spotting. The hand location procedure detects the candidated regions on the basis of skin color and motion in an image by using a color histogram matching and time-varying edge difference techniques. The hand tracking algorithm finds the centroid of a moving hand region, connect those centroids, and produces a trajectory. The spotting algorithm divides the trajectory into real and meaningless gestures. In constructing a feature database, the proposed approach uses the weighted ρ-φ-ν feature code, and employ a k-means algorithm for the codebook of HMM. In our experiments, 1,300 alphabetical and 1,300 untrained gestures are used for training and testing, respectively. Those experimental results demonstrate that the proposed approach yields a higher and satisfactory recognition rate for the images with different sizes, shapes and skew angles.
ER -