检索结果-内蒙古大学图书馆

Multitask bilateral learning for real-time image enhancement

JOURNAL OF THE SOCIETY FOR INFORMATION DISPLAY 2019年第10期27卷 630-645页

作者： Kong, Kyeongbo Lee, Junggi Song, Woo-Jin Kang, Minsung Kwon, Kyung Joon Kim, Seong Gyun Pohang Univ Sci & Technol Dept Elect Engn 77 Cheongam Ro Pohang 37673 Gyungbuk South Korea LG Display Seoul South Korea

Nowadays, deep neural networks (DNNs) for image processing are becoming more complex;thus, reducing computational cost is increasingly important. This study highlights the construction of a DNN for real-time image processing, training various image processing operators efficiently through multitask learning. For real-time image processing, the proposed algorithm takes a joint upsampling approach through bilateral guided upsampling. For multitask learning, the overall network is based on an encoder-decoder architecture, which consists of encoding, processing, and decoding components, in which the encoding and decoding components are shared by all the image processing operators. In the processing component, a semantic guidance map, which contains processing information for each image processing operator, is estimated using simple linear shifts of the shared deep features. Through these components, the proposed algorithm requires an increase of only 5% in the number of parameters to add another image processing operator and achieves faster and higher performance than that of deep-learning-based joint upsampling methods in local image processing as well as global image processing.

关键词： bilateral grid deep learning local image processing multitask learning real-time image processing

来源：评论

学校读者我要写书评

暂无评论

Interconnected Neural Networks Based on Voting Scheme and local Detectors for Retinal image Analysis and Diagnosis 19th

Interconnected Neural Networks Based on Voting Scheme and Lo...

引用

19th International Conference on image Analysis and processing (ICIAP)

作者： Caramihale, Traian Popescu, Dan Ichim, Loretta Univ Politehn Bucuresti Fac Automat Control & Comp Bucharest Romania Stefan S Nicolau Inst Virol Bucharest Romania

ISBN: (纸本)9783319685489;9783319685472

This paper presents a method for accurate detection and localization of important regions of interest (ROIs) for retinal disease diagnosis: optic disc, macula, blood vessels, exudates and hemorrhages. To this end, the image processing is made on patches of different dimensions, obtained by combining sliding box and non-overlapping box algorithms. Two interconnected neural networks are considered: one for feature selection and class representative establishment (learning phase) and one for the classification phase: ROIs detection, localization, segmentation and evaluation. The last one is based on a voting scheme of local detectors with different weights, taking into account the results from associated confusion matrices. The information is fused from the selected features (textural type and fractal type, which are computed for different color channels). We tested 200 images from different public databases (40 for the learning phase and 160 for the classification phase). The experimental results indicate a good accuracy for all analyzed regions of retinal images.

关键词： image segmentation Neural networks local image processing Retinal disease diagnosis Voting scheme

来源：评论

学校读者我要写书评

暂无评论

Memoization-based high-performance video frame processing

引用

JOURNAL OF ELECTRONIC IMAGING 2016年第6期25卷 63025.1-63025.1页

作者： Farzmahdi, Mojtaba Luo, Rong Tsinghua Univ Dept Elect Beijing 100084 Peoples R China

We present a high-performance improvement method for implementation of local processing algorithms for video frames by using the benefit of memoization technique. Memoization is a technique that uses the advantage of data redundancy to minimize the amount of computations performed by retrieving previous results instead of computing again, which leads to faster processing speed. In this method, the benefit of interframe redundancy in adjacent frames is used for memoizing where the pixels in a sequence of frames are correlated. We have developed this method in software and applied it to edge detection and median filters. The typical speedups achieved in the median filter range from 2.2x with exact results to 6.48x in tolerant methods and in edge detection filter range from 2.1x with exact results to 5.41x in tolerant method. The structural similarity index metric that is used for evaluating the perceived similarity of the tolerant result with ideal result was applied to each adjacent frame in sample stream frames. The typical values of this parameter were 0.96 in median filter and 0.71 in edge detection filter. (C) 2016 SPIE and IS&T

关键词： memoization local image processing interframe redundancy homogeneity structural similarity index metric

来源：评论

学校读者我要写书评

暂无评论

Lukasiewicz ANN for local image processing

引用

NEURAL NETWORK WORLD 2005年第6期15卷 535-551页

作者： Majerová, D Kukal, J Prague Univ Chem Technol Prague 16628 6 Czech Republic

One of the useful areas of the 2D image processing is called de-noising. When both original (ideal) and noisy images are available, the quality of de-noising is measurable. Our paper is focused to local 2D image processing using Lukasiewicz algebra with the square root function. The basic operators and functions in given algebra are first defined and then analyzed. The first result of the fuzzy logic function (FLF) analysis is its decomposition and realization as Lukasiewicz network (LN) with three types of processing nodes. The second result of FLF decomposition is the decomposed Lukasiewicz network (DLN) with dyadic preprocessing and two types of processing nodes. The decomposition chain, which begins with FLF and converts it to LN and then to DLN, terminates as Lukasiewicz artificial neural network (LANN) with dyadic preprocessing and only one type of processing node. Then the LANN is able to learn its integer weights in the ANN style. We are able to realize a set of individual FLF filters as LANN. Their preprocessing strategies are based on the pixel neighborhood, sorted list, Walsh list, and L-estimates. The quality of de-noising can be improved via compromise filtering. Two types of compromise de-noising filters are also realizable as LANN. One of them is called constrained referential neural network (CRNN). The other one is called dyadic weight neural network (DWNN). The compromise filters operate with the values from the set of individual filters. Both CRNN and DWNN are able to increase the quality of image processing as demonstrated on the biomedical MR image. All the calculations are realized in the Matlab environment.

关键词： Lukasiewicz algebra square root neural network local image processing

来源：评论

学校读者我要写书评

暂无评论

Optical implementations of threshold decomposition and morphological operations with dual-rail processing

Optical implementations of threshold decomposition and morph...

引用

Conference on Photonic Devices and Algorithms for Computing VI

作者： Buczynski, R Szoplik, T Thienpont, H Warsaw Univ Fac Phys Informat Opt Grp PL-02093 Warsaw Poland

ISBN: (纸本)081945494X

Fast parallel processing of gray-scale images and exact hard-clip thresholding are two important functionalities necessary in optoelectronic implementations of structural processors. The parallel nature of processing stems from optical implementation of local operations with arrays of active smart pixels. We have demonstrated a morphological image processor composed of arrays of bistable optoelectronic transceivers which are connected in differential pairs and work as comparators. The use of differential pairs of optical thyristors fabricated in GaAs technology allows to realize a dual rail architecture for this photonic morphological image processor. The processor consists of a thresholding module and a binary morphological processing module. The thresholding module decomposes gray level images into series of binary slices. In the binary morphological processing module operations are performed within a neighborhood defined by a structuring element implemented as a diffractive fan-out element. In the prototype set-up we demonstrate median filtering, dilation and erosion operations performed for an image of 8x8 pixels and threshold decomposition of 6 gray level images. In principle all rank order as well as morphological filters can be optically calculated in the set-up. Additional functionality of the processor is achieved with use of the electronic layer with digital cellular processors. The electronic layer, designed as an array of simple digital processors, realizes a set of operations on binary images using 4 bit programmable weights. Simulation results for 0.8 mum CMOS technology are presented. We discuss the limitations of the photonic morphological image processing with respect to bandwidth, parallelism and architecture of the processor.

关键词： local image processing smart pixels mathematical morphology photonic processors threshold decomposition

来源：评论

学校读者我要写书评

暂无评论

Tele-Operative System for Bioproduction - Remote local image processing for Object Identification

引用

IFAC Proceedings Volumes 2000年第29期33卷 191-194页

作者： Si Chan Kim Heon Hwang Jung Eek Son Dong Yup Choi Robotics & Vision Lab. Dept. of Bio-Mechatronic Engineering Faculty of Life Science & Technology Sungkyunkwan University Kyungki-do Suwon-si Changan-gu 440-746 KOREA Dept. of Horticulture College of Agri culture & Life Science Seoul National University Kyungki-do Suwon-si Kwonsun-gu 441-744 KOREA Automation Dept. Daelim college Kyungki-do Anyang-si Dongan-gu 431-715 KOREA

This paper introduces a new concept of automation for bio-production with tele-operative system. The proposed system showed practical and feasible way of automation for the volatile bio-production process. Based on the proposition, recognition of the job environment with object identification was performed using computer vision system. A man-machine interactive hybrid decision-making, which utilized a concept of tele-operation was proposed to overcome limitations of the capability of computer in image processing and feature extraction from the complex environment image. Identifying watermelons from the outdoor scene of the cultivation field was selected to realize the proposed concept. Identifying watermelon from the camera image of the outdoor cultivation field is very difficult because of the ambiguity among stems, leaves, shades, and especially fruits covered partly by leaves or stems. The analog signal of the outdoor image was captured and transmitted wireless to the host computer by R. F module. The localized window was formed from the outdoor image by pointing to the touch screen. And then a sequence of algorithms to identify the location and size of the watermelon was performed with the local window image. The effect of the light reflectance of fruits, stems, ground, and leaves were also investigated.

关键词： local image processing Tele-operation Feature Extraction Bio-production Real Time Control Watermelon

来源：评论

学校读者我要写书评

暂无评论

Photonic morphological image processing

Photonic morphological image processing

引用

Conference on Optoelectronic Information processing - Optics for Information Systems

作者： Buczynski, R Szoplik, T Veretennicoff, I Thienpont, H Free Univ Brussels Dep Appl Phys & Photon B-1050 Brussels Belgium

ISBN: (纸本)0819441236

We have demonstrated a morphological image processor composed of arrays of bistable optoelectronic transceivers which are connected in differential pairs and work as comparators. The use of differential pairs of optoelectronic thyristors suggested a dual rail architecture for this Photonic Morphological image Processor (PMIP). The PMIP consists of a thresholding module, that decomposes grey level images into binary slices, and a binary morphological processing module. Morphological operations are performed within a neighbourhood defined by a structuring element implemented as a diffractive fan-out element. We demonstrate dilation and erosion operations performed at a 100 Hz frame rate for an image of 8x8 pixels and threshold decomposition of 6 grey level images is demonstrated at a 1,800 Hz rate. In this paper we also discuss the limitations of photonic morphological image processing with respect to speed, bandwidth, parallelism and architecture.

关键词： local image processing smart pixels mathematical morphology optoelectronic processors photonic processors optical thyristors threshold decomposition

来源：评论

学校读者我要写书评

暂无评论

Identification and 3D Coordinate Extraction of Object Via Tele-Task Command

引用

IFAC Proceedings Volumes 2001年第11期34卷 111-116页

作者： Si Chan Kim Heon Hwang Dong Yup Choi

Major deficiencies of current automation scheme including various robots for bioproduction include the lack of task adaptability and real time processing, low job performance for diverse tasks, and the lack of robustness of task results, high system cost, failure of the credit from the operator, and so on This paper proposed a scheme that could solve the current limitation of task abilities of conventional computer controlled automatic system. The proposed scheme is the man-machine hybrid automation via tele-operation which can handle various Coproduction processes And it was classified into two categories One category was the efficient task sharing between operator and CCM (computer controlled machine) The other was the efficient interface between operator and CCM To realize the proposed concept, task of the object identification and extraction of 3D coordinate of an object was sclectcd 3D coordinate information was obtained from cantera calibration using camera as a measxirement device Two stereo images were obtained by moving a camera certain distance in horizontal direction normal to focal axis and by acquiring two images at different locations Transformation matrix for camera calibration was obtained via least square error approach using specified 6 known pairs of data points in 2D image and 3D world space 3D world coordinate was obtained from two sets of image pixel coordinates of both camera images with calibrated transformation matrix As an interface system between operator and CCM, a touch pod screen mounted on the monitor and remotely captured imaging system were used Object indication was done by the operator's finger touch to the captured image using the touch pad screen A certain size of local image processing area was specified after the touch was made. And image processing was performed with the specified local area to extract desired features of the object An MS Window s based interface software was developed using Visual C++6.0 The software was deve

关键词： Tele-task Command Man-machine Interface 3D Coordinate Extraction local image processing Object Identification

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：