Papers by Shyi-Chyi Cheng
Sensors, Oct 7, 2022
This article is an open access article distributed under the terms and conditions of the Creative... more This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY
Applied sciences, Dec 22, 2022
This article is an open access article distributed under the terms and conditions of the Creative... more This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY
Journal of Experimental Botany
The pollen grains of Phalaenopsis orchids are clumped tightly together, packed in pollen dispersa... more The pollen grains of Phalaenopsis orchids are clumped tightly together, packed in pollen dispersal units called pollinia. In this study, the morphology, cytology, biochemistry, and sucrose transporters in pollinia of Phalaenopsis orchids were investigated. Histochemical detection was used to characterize the distribution of sugars and callose at the different development stages of pollinia. Ultra-performance liquid chromatography-high resolution-tandem mass spectrometry data indicated that P. aphrodite accumulated abundant saccharides such as sucrose, galactinol, myo-inositol, and glucose, and trace amounts of raffinose and trehalose in mature pollinia. We found that galactinol synthase (PAXXG304680) and trehalose-6-phosphate phosphatase (PAXXG016120) genes were preferentially expressed in mature pollinia. The P. aphrodite genome was identified as having 11 sucrose transporters (SUTs). Our qRT–PCR confirmed that two SUTs (PAXXG030250 and PAXXG195390) were preferentially expressed in...
2021 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS), 2021
The challenge in stereo matching for underwater 3D object modeling is to compute dense depth data... more The challenge in stereo matching for underwater 3D object modeling is to compute dense depth data with the minimal smoothness at high frame rate. To address this issue, in this paper we propose an object based stereo matching for underwater 3D fish reconstruction using convolutional neural networks (CNNs). For each image in a stereo frame, an instance segmentation CNN is used to segment fish objects from the background. The set of fish objects in the left image is matched against those in the right to detect the object pairs using the proposed support-weights approach. For each pair, the common disparity value is then computed. Next, fish objects in these images are cropped and matched to do the pixel-wise residual disparity computation using the video interpolation CNN. The computed fish disparities and depth values are finally used to estimate the sizes of fish. Instead of estimating the fish length using a single frame, we track each fish across frames of the input stereo video to compute the fish length frame by frame. The mean fish length is finally computed as the result. An underwater dataset with the fish actual length measured by human is constructed to verify the effectiveness of our approach. Experimental results show that the error rate of the proposed approach is less than 6%.
2021 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS), 2021
In this paper, we present a novel 3D structure-awareness image-based point cloud compression sche... more In this paper, we present a novel 3D structure-awareness image-based point cloud compression scheme, which applies the proposed Symmetry based Convolutional Neural Pyramid (SCNP) to compress colored point clouds view-by-view for 3D model transmission. Input a 3D model to the system, a preprocessing step is first applied to represent the input point cloud as a sequence of view-specific six-dimensional (6D) images, where each pixel is characterized by an RGB color vector and a XYZ 3D point. The transformed 6D images preserve the regular grid structure and thus the redundant information is easy to be removed by conventional image/video compression techniques. Our SCNP first represents each 6D image as a multiple-level pyramid structure for progressively compressing and transmission. The lowest resolution image at the highest level of the pyramid is then decomposed into multiple patches with each of them being coded as the index of a small dictionary through vector quantization. The residual images at other levels are also represented by the vector quantization codes with different patch sizes for progressively reconstructing the input colored point cloud. This process results in a multiple description coding scheme for 3D point cloud compression. With the pre-learned set of dictionaries, the projected view-specific 6D images of the input 3D model are encoded one-by-one to obtain the compressed results for 3D model transmission. In the receiver end, the 3D model is reconstructed by merging all the reconstructed point clouds where each of them is decoded from the corresponding view-specific image. Finally, the conventional 3D reconstruction approach has been applied to remove redundant 3D points for reconstructing the 3D model. Experiments demonstrate the effectiveness of our approach which attains better performance than the current state-of-the-art point cloud compression methods.
2016 23rd International Conference on Pattern Recognition (ICPR), 2016
In this paper we present a novel unsupervised feature representation by extracting salient symmet... more In this paper we present a novel unsupervised feature representation by extracting salient symmetries in RGB-D images using the proposed moment-based symmetric patch detector. A fast indexing structure is also derived to group local symmetric patches into semantically meaningful symmetric parts. Given an RGB-D image, the hash-based symmetric patch indexing speeds up the searches of symmetric patch pairs, which are further grouped into symmetric parts with nearly linear time complexity. In the context of symmetry matching and scene classification, the second part of this work presents a symmetry-based scene modeling, aiming at computing a robust part-based feature set for each image category. To verify the effectiveness of the symmetry detector, based on the pre-learned part-based scene model, a part-based voting scheme is constructed to annotate the scene type of the input RGB-D image. Experimental results show that the proposed approach outperforms the compared methods in terms of ...
Aquacultural Engineering, 2021
Abstract This paper presents a novel method to evaluate fish feeding intensity for aquaculture fi... more Abstract This paper presents a novel method to evaluate fish feeding intensity for aquaculture fish farming. Determining the level of fish appetite helps optimize fish production and design more efficient aquaculture smart feeding systems. Given an aquaculture surveillance video, our goal is to improve fish feeding intensity evaluation by proposing a two-stage approach: an optical flow neural network is first applied to generate optical flow frames, which are then inputted to a 3D convolution neural network (3D CNN) for fish feeding intensity evaluation. Using an aerial drone, we capture RGB water surface images with significant optical flows from an aquaculture site during the fish feeding activity. The captured images are inputs to our deep optical flow neural network, consisting of the leading neural network layers for video interpolation and the last layer for optical flow regression. Our optical flow detection model calculates the displacement vector of each pixel across two consecutive frames. To construct the training dataset of our CNNs and verify the effectiveness of our proposed approach, we manually annotated the level of fish feeding intensity for each training image frame. In this paper, the fish feeding intensity is categorized into four, i.e., ‘none,’ ‘weak,’ ‘medium’ and ‘strong.’ We compared our method with other state-of-the-art fish feeding intensity evaluations. Our proposed method reached up to 95 % accuracy, which outperforms the existing systems that use CNNs to evaluate the fish feeding intensity.
International Workshop on Advanced Imaging Technology (IWAIT) 2020, 2020
This paper presents a novel deep-learning approach to analyze the fish feeding intensity based on... more This paper presents a novel deep-learning approach to analyze the fish feeding intensity based on the images of fish tanks during the fish feeding process. The grade of the fish feeding intensity is an important indicator of fish appetite. On the design of a smart feeding system in aquaculture, this information is of great significance for guiding feeding and optimizing the fish production. However, conventional fish appetite assessment methods are inefficient and subjective. To solve these problems, in this study, based on a space-time two-stream 3D CNN, a deep learning approach for grading fish feeding intensity is proposed to evaluate fish appetite. The flow of the approach is implemented as follows. First, a fixed RGB camera is setup to capture the videos from the fish tanks during the feeding processes. This also constructs a dataset for training the two-stream neural network, and the fish appetite levels are graded using the trained neural network model. Finally, the performance of the method is evaluated and compared with other CNN-based deep learning approaches. The results show that the grading accuracy reached 91.18%, which outperforms the compared CNN-based approaches. Thus, the model can be used to detect and evaluate fish appetite to guide production practices.
Multimedia Tools and Applications, 2018
Proceedings of 2004 International Symposium on Intelligent Signal Processing and Communication Systems, 2004. ISPACS 2004.
ABSTRACT This paper is focused on the design of the indexing structure for high-dimensional image... more ABSTRACT This paper is focused on the design of the indexing structure for high-dimensional image databases by principal axis analysis. Firstly, we present the method of constructing the projection line with minimum inertia by principal axis analysis. Secondly, the proposed filtering mechanism, based on the projection scores of the database vectors, is presented. Then follows a method to enhance the discriminatory power of the approximations by incorporating the projection scores on multiple principal axes. Finally, some experimental tests to illustrate the effectiveness of our method are shown.
2008 International Symposium on Intelligent Signal Processing and Communications Systems, 2009
ABSTRACT It is desirable and yet remains as a challenge for querying multimedia data by finding a... more ABSTRACT It is desirable and yet remains as a challenge for querying multimedia data by finding an object inside a target image. The effectiveness of region-based representation for content-based image retrieval is extensively studied in the literature. One common weakness of the region-based approaches only in terms of regions' low-level visual features is that the homogeneous image regions have little correspondence to the semantic objects, thus, the retrieval results are often far from satisfactory. In addition, the performance is also ruled by the consistency of the segmentation result of the region of the target object in the query and target images. Instead of solving these problems independently, in this paper, a region-based object retrieval using the generalized Hough transform (GHT) and content aware image segmentation is proposed. The proposed approach has two phases. First, the learning phase finds and stores the stable parameters for segmenting each database image, and then sorts the database images according to the found segmentation parameters. In the retrieval phase, an incremental image segmentation process based on the stored segmentation parameters is performed to segment a query image into regions for retrieving visual objects inside database images through the GHT with a modified voting scheme for locating the target visual object under the geometry transformation. With the learned parameters for image segmentation, the segmentation results of query and target images are more stable and consistent. Computer simulation results show that the proposed method gives good performance in terms of retrieval accuracy, robustness, and execution speed.
2005 IEEE International Symposium on Circuits and Systems
ABSTRACT This paper presents a fast segmentation of moving objects in video sequences using the m... more ABSTRACT This paper presents a fast segmentation of moving objects in video sequences using the moment-preserving technique. The emerging video coding standard MPEG-4 enables various content-based functionalities for multimedia applications. To decompose each frame of a video sequence into video object planes (VOP) is the first step for MPEG-4 toward supporting such functionalities, as well as improving coding efficiency. Each VOP corresponds to a single moving object in the scene. For this purpose, we propose a novel region-based segmentation method as a general VOP segmentation algorithm by estimating the motion vector of each region in a VOP using the proposed moment-preserving technique. An initial spatial partition of each frame is obtained by a fast, region-growing image segmentation algorithm. The solution to the motion vector of each region in a VOP is analytic. This algorithm can be performed very fast for content-based multimedia applications with no need for special hardware. Experimental results for several video sequences demonstrate the effectiveness of the proposed approach.
2011 International Conference on Complex, Intelligent, and Software Intensive Systems, 2011
In this paper, the self organization properties of genetic algorithms are employed to tackle the ... more In this paper, the self organization properties of genetic algorithms are employed to tackle the problem of feature selection and extraction in ultrasound images, which can facilitate early disease detection and diagnosis. Accurately identifying the aberrant features at a particular location of clinical ultrasound images is important to find the possibly damaged tissues. Unfortunately, it is difficult to exactly detect
2010 Sixth International Conference on Intelligent Information Hiding and Multimedia Signal Processing, 2010
... Chi-Han Chuang , Yung-Chi-Lo Department of Computer Science and Engineering, National Taiwan ... more ... Chi-Han Chuang , Yung-Chi-Lo Department of Computer Science and Engineering, National Taiwan Ocean University Keelung, Taiwan [email protected] ... The image stabilization method proposed by Xu and Lin [3] is also implemented for performance comparison. ...
2009 International Conference on Complex, Intelligent and Software Intensive Systems, 2009
In this paper, the self organization properties of ant colonies are employed to tackle the proble... more In this paper, the self organization properties of ant colonies are employed to tackle the problem of DNA copy number analysis in array CGH data, which can reveal chromosomal aberrations in the genomic DNA. These amplifications and deletions may be crucial events in the development and progression of cancer and other diseases. Accurately identifying the recurrent aberration at a particular
2013 IEEE International Symposium on Circuits and Systems (ISCAS2013), 2013
This paper presents an approach to detect moving and static objects occurring in a video by a nov... more This paper presents an approach to detect moving and static objects occurring in a video by a novel model-based tracking. The method exploits the spatial and motion coherence of objects across image frames that results from the known bounded shape distortion and object's velocity between two consecutive frames. The interframe transformation space is thus reduced to a reasonable small space of only tens or hundreds of possible states. Considering each state as a class, the object tracking process to locate objects across frames can be implemented by a classification framework, comprising a Hough-voting framework and a class-specific implicit video object model. Given a frame of the input video clip, we divide each frame of a test video clip into multiple patches which search similar model patches in the learnt implicit video object model to locate the target objects from the frames. Patch similarity is defined with respect to appearance and motion features of patches. Results show that the proposed method gives good performance on several publicly available datasets in terms of detection accuracy.
2009 Fifth International Conference on Intelligent Information Hiding and Multimedia Signal Processing, 2009
ABSTRACT A new watermarking scheme on 3D triangular mesh models is proposed. Watermarks are embed... more ABSTRACT A new watermarking scheme on 3D triangular mesh models is proposed. Watermarks are embedded by modifying a subset of carefully selected edge vertices in order to resist attacks. A local geometrical disturbance on the selected edge vertices is used to embed the information without destroying the local connectivity. Edge vertices are detected using the proposed 3D moment-preserving technique. Edge vertices quantize into multiple classes where each of them is used to embed a watermark bit. Experimental results show that the proposed scheme is robust in resisting common attacks.
International MultiConference of Engineers and Computer Scientists, 2007
The invention provides novel phenoxyalkylcarboxylic acids which are useful in therapy as metaboli... more The invention provides novel phenoxyalkylcarboxylic acids which are useful in therapy as metabolic regulators and in agriculture as selective herbicides.
2006 International Conference on Image Processing, 2006
This paper proposes an object-based image retrieval using a method based on visual pattern matchi... more This paper proposes an object-based image retrieval using a method based on visual pattern matching. A visual pattern is obtained by detecting the line edge from a square block using the moment-preserving edge detector. It is desirable and yet remains as a challenge for querying multimedia data by finding an object inside a target image. Given an object model, an
Uploads
Papers by Shyi-Chyi Cheng