scholarly journals Analysis of the Current Situation of Piano Education in Colleges and Universities in the Information Age and Research on Countermeasures

CONVERTER ◽  
2021 ◽  
pp. 574-582
Author(s):  
Yuan Shuhui
Keyword(s):  
Skin Color ◽  
Template Matching ◽  
Music Majors ◽  
Depth Sensor ◽  
Transition Diagram ◽  
Piano Teaching ◽  
Depth Images ◽  
Piano Education ◽  
Template Library ◽  
Background Difference

In view of the low application ability of piano improvisational accompaniment of music majors, this paper proposes a method of big data combined with MIDI keyboard and Kinect depth sensor to achieve the purpose of recognizing chord progression and judging fingering when students perform, and realizes the auxiliary teaching system. Firstly, the information of color and depth images is obtained, and the state transition diagram of chord transposition and chord gesture template library are constructed as the system initialization conditions. Secondly, using the traditional skin color modeling and background difference method as well as the current depth data, the gesture recognition is realized by template matching. Finally, the correctness of chord progression is judged, and comprehensive fingering application is used to score and evaluate. The experimental results show that the system has high robustness and can be effectively applied to piano teaching.

scholarly journals RFaNet: Receptive Field-Aware Network with Finger Attention for Fingerspelling Recognition Using a Depth Sensor

Mathematics ◽  
2021 ◽  
Vol 9 (21) ◽  
pp. 2815
Author(s):  
Shih-Hung Yang ◽  
Yao-Mao Cheng ◽  
Jyun-We Huang ◽  
Yon-Ping Chen
Keyword(s):  
Receptive Field ◽  
American Sign Language ◽  
Multiple Scales ◽  
Receptive Fields ◽  
Depth Image ◽  
Small Scale ◽  
Feature Maps ◽  
Depth Sensor ◽  
Depth Images ◽  
Effective Transfer

Automatic fingerspelling recognition tackles the communication barrier between deaf and hearing individuals. However, the accuracy of fingerspelling recognition is reduced by high intra-class variability and low inter-class variability. In the existing methods, regular convolutional kernels, which have limited receptive fields (RFs) and often cannot detect subtle discriminative details, are applied to learn features. In this study, we propose a receptive field-aware network with finger attention (RFaNet) that highlights the finger regions and builds inter-finger relations. To highlight the discriminative details of these fingers, RFaNet reweights the low-level features of the hand depth image with those of the non-forearm image and improves finger localization, even when the wrist is occluded. RFaNet captures neighboring and inter-region dependencies between fingers in high-level features. An atrous convolution procedure enlarges the RFs at multiple scales and a non-local operation computes the interactions between multi-scale feature maps, thereby facilitating the building of inter-finger relations. Thus, the representation of a sign is invariant to viewpoint changes, which are primarily responsible for intra-class variability. On an American Sign Language fingerspelling dataset, RFaNet achieved 1.77% higher classification accuracy than state-of-the-art methods. RFaNet achieved effective transfer learning when the number of labeled depth images was insufficient. The fingerspelling representation of a depth image can be effectively transferred from large- to small-scale datasets via highlighting the finger regions and building inter-finger relations, thereby reducing the requirement for expensive fingerspelling annotations.

Robust Face Detection Combined Skin Color Features, Template Matching and VQ Histogram Method in Practical Environments

2004 ◽  
Vol 10 (2) ◽  
pp. 143-153 ◽  
Author(s):  
Qiu Chen ◽  
Koji Kotani ◽  
Yoshiyuki Taniguchi ◽  
Zhibin Pan ◽  
Tadahiro Ohmi
Keyword(s):  
Face Detection ◽  
Skin Color ◽  
Template Matching ◽  
Histogram Method ◽  
Color Features

scholarly journals Hand Gesture Recognition Using PCA, KNN and SVM

2019 ◽  
pp. 547-550
Author(s):  
Julakanti Likhitha Reddy ◽  
Bhavya Mallela ◽  
Lakshmi Lavanya Bannaravuri ◽  
Kotha Mohan Krishna
Keyword(s):  
Gesture Recognition ◽  
Skin Color ◽  
Template Matching ◽  
Hand Gesture Recognition ◽  
Support Vector ◽  
Hand Gesture ◽  
Color Model ◽  
Language Recognition ◽  
Sign Language Recognition ◽  
Skin Color Model

To interact with world using expressions or body movements is comparatively effective than just speaking. Gesture recognition can be a better way to convey meaningful information. Communication through gestures has been widely used by humans to express their thoughts and feelings. Gestures can be performed with any body part like head, face, hands and arms but most predominantly hand is use to perform gestures, Hand Gesture Recognition have been widely accepted for numerous applications such as human computer interactions, robotics, sign language recognition, etc. This paper focuses on bare hand gesture recognition system by proposing a scheme using a database-driven hand gesture recognition based upon skin color model approach and thresholding approach along with an effective template matching with can be effectively used for human robotics applications and similar other applications .Initially, hand region is segmented by applying skin color model in YCbCr color space. Y represents the luminance and Cb and Cr represents chrominance. In the next stage Otsu thresholding is applied to separate foreground and background. Finally, template based matching technique is developed using Principal Component Analysis (PCA), k-nearest neighbour (KNN) and Support Vector Machine (SVM) for recognition. KNN is used for statistical estimation and pattern recognition. SVM can be used for classification or regression problems.

scholarly journals Face Detection in a Mixed-Subject Document

2016 ◽  
Vol 6 (6) ◽  
pp. 2828
Author(s):  
Lhoussaine Bouhou ◽  
Rachid El Ayachi ◽  
Mohamed Baslam ◽  
Mohamed Oukessou
Keyword(s):  
Face Detection ◽  
Skin Color ◽  
Template Matching ◽  
Detection System ◽  
Second Phase ◽  
Text And Image ◽  
Important Research Topic ◽  
The Face ◽  
Second Category ◽  
Text Images

<p>Before you recognize anyone, it is essential to identify various characteristics variations from one person to another. among of this characteristics, we have those relating to the face. Nowadays the detection of skin regions in an image has become an important research topic for the location of a face in the image. In this research study, unlike previous research studies  related  to  this  topic  which  have  focused  on  images  inputs  data  faces,  we  are  more interested to the fields face detection in mixed-subject documents (text + images). The face detection system developed is based on the hybrid method to distinguish two categories of objects from the mixed document. The first category is all that is text or images containing figures having no skin color, and the second category is any figure with the same color as the skin. In the second phase the detection system is based on Template Matching method to distinguish among the figures of the second category only those that contain faces to detect them. To validate this study, the system developed is tested on the various documents which including text and image.</p>

Dimensions of the Modern Pig

2018 ◽  
Vol 61 (5) ◽  
pp. 1729-1739 ◽  
Author(s):  
Isabella C. F. S. Condotta ◽  
Tami M. Brown-Brandl ◽  
John P. Stinn ◽  
Gary A. Rohrer ◽  
Jeremiah D. Davis ◽  
...  
Keyword(s):  
Animal Husbandry ◽  
Finishing Pigs ◽  
Depth Sensor ◽  
Livestock Farming ◽  
Body Depth ◽  
Depth Images ◽  
Engineering Standards ◽  
Feed Form ◽  
Current Engineering ◽  
Physical Dimensions

Abstract. It is important to know the physical dimensions of livestock to properly design confined animal housing facilities as well as feeding and drinking equipment. An engineering standard for the dimensions of livestock and poultry published by ASABE reports swine dimensions that were originally published in 1968. Changes in animal husbandry practices for swine, such as improved and new genetic lines, nutrition and feed form, and improved facility and equipment design, make it necessary to validate or update these dimensions for modern animals. The objective of this study was to evaluate dimension data for the grow-finish stages of modern pigs. A total of 150 growing-finishing pigs were sampled at five approximate ages: 4, 8, 12, 16, and 20 weeks old (30 animals at each age). The animals equally represented three commercial sire lines (Landrace, Duroc, and Yorkshire), and equal numbers of barrows and gilts were sampled. Dorsal and lateral color digital and depth images were collected using a Kinect sensor as the pigs were held individually in a stanchion or scale, and the images were analyzed by manual and automated methods. Measured physical dimensions included height from top of back to the floor, length from nose to base of the tail, width at shoulders, jowl length, front leg height, body depth from top of back to lowest point of the belly, and others. It was determined that the conformation of modern pigs has changed from the dimensions reported in current engineering standards such that modern pigs tend to be wider (15.1%) and shorter in height (-10.2%) and length (-4.9% on average) between 4 and 20 weeks of age. These updated pig dimensions will enable engineers to better design modern swine equipment and facilities. Keywords: Depth sensor, Dimensions, Image analysis, Precision livestock farming, Swine.

Sign in / Sign up

Export Citation Format

Share Document