Supervised Hashing with RBF Kernel and Convolution for Hyperspectral image classification

نویسندگان

چکیده

é«˜å ‰è°±é¥æ„Ÿå¯åŒæ­¥èŽ·å–åœ°è¡¨è¦†ç›–ç©ºé—´å½±åƒå’Œè¿žç»­ä¸”ç²¾ç»†çš„å ‰è°±æ•°æ®ï¼Œèƒ½å¤Ÿå®žçŽ°å¯¹åœ°ç‰©çš„ç²¾ç»†åˆ†ç±»ä¸Žè¯†åˆ«ã€‚ç„¶è€Œï¼Œé«˜å ‰è°±å›¾åƒçš„é«˜ç»´ç‰¹æ€§å¯¹åˆ†ç±»å¸¦æ¥å·¨å¤§æŒ‘æˆ˜ã€‚ä¸ºæ­¤ï¼Œæœ¬æ–‡æŽ¢è®¨äº†ä¸€ç§åŸºäºŽå·ç§¯æ ¸å“ˆå¸Œå­¦ä¹ çš„é«˜å ‰è°±å›¾åƒåˆ†ç±»æ–¹æ³•ã€‚å“ˆå¸Œå­¦ä¹ å¯ä»¥å°†é«˜ç»´ä¿¡æ¯è¡¨è¾¾ä¸ºä½Žç»´å“ˆå¸Œç¼–ç ï¼Œé€šè¿‡è®¡ç®—å“ˆå¸Œç¼–ç å† ç§¯å¹¶å€ŸåŠ©æœ€å°æ±‰æ˜Žè·ç¦»å®žçŽ°åˆ†ç±»ã€‚ä¸ºäº†æœ‰æ•ˆè¡¨è¾¾éžçº¿æ€§æ•°æ®ï¼Œåˆå‘å±•äº†æ 方法。然而,直接应用æ è¿›è¡Œé«˜å ‰è°±å›¾åƒåˆ†ç±»å­˜åœ¨è¿è¡Œé€Ÿåº¦æ ¢å’Œæœªè€ƒè™‘ç©ºé—´é‚»åŸŸä¿¡æ¯çš„ä¸è¶³ã€‚ä¸ºæ­¤ï¼Œæœ¬æ–‡åœ¨æ ä¸­å¼•å ¥å¾„å‘åŸºå‡½æ•°RBF(Radial Basis Function)作为损失函数以提高运行效率;同时,借助四维卷积操作å åˆ†è¡¨è¾¾ç©ºé—´é‚»åŸŸä¿¡æ¯ï¼Œæå‡ºäº†åŸºäºŽå·ç§¯æ ‰è°±å›¾åƒåˆ†ç±»æ–¹æ³•CKSH(Supervised Hashing with RBF Kernel and Convolutionï¼‰ï¼ŒåŒæ—¶æŽ¢è®¨äº†è¯¥æ–¹æ³•åœ¨ä» åˆ©ç”¨å ‰è°±ç‰¹å¾å’Œå ‰è°±â€”ç©ºé—´è”åˆç‰¹å¾ä¸Šçš„åˆ†ç±»æ•ˆæžœã€‚åœ¨å›½é™ é€šç”¨æµ‹è¯•æ•°æ®Indian Pines和University of Pavia上进行了实验,结果表明:本文提出的CKSHæ–¹æ³•ä¼˜äºŽä¼ ç»Ÿåˆ†ç±»æ–¹æ³•ï¼ˆæ”¯æŒå‘é‡æœºã€éšæœºå­ç©ºé—´ï¼‰å’Œå ¶ä»–å“ˆå¸Œå­¦ä¹ æ–¹æ³•ï¼ˆå¦‚è°±å“ˆå¸Œã€çƒå“ˆå¸Œã€ç›‘ç£ç¦»æ•£å“ˆå¸Œã€æ½œåœ¨å› å­å“ˆå¸Œç­‰ï¼‰ï¼ŒåŒæ—¶åœ¨ä¸åŒè®­ç»ƒæ ·æœ¬æ•°é‡æ¡ä»¶ä¸‹å‡å–å¾—äº†è¾ƒé«˜çš„åˆ†ç±»ç²¾åº¦ï¼Œè¾¾åˆ°96.12%(Indian Pines,10%çš„è®­ç»ƒæ ·æœ¬ï¼‰å’Œ98.00%(University Pavia,5%çš„è®­ç»ƒæ ·æœ¬ï¼‰ï¼Œä»Žè€ŒéªŒè¯äº†è¯¥æ–¹æ³•çš„æœ‰æ•ˆæ€§ã€‚

برای دانلود باید عضویت طلایی داشته باشید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Kernel-Based Supervised Discrete Hashing for Image Retrieval

Recently hashing has become an important tool to tackle the problem of large-scale nearest neighbor searching in computer vision. However, learning discrete hashing codes is a very challenging task due to the NP hard optimization problem. In this paper, we propose a novel yet simple kernel-based supervised discrete hashing method via an asymmetric relaxation strategy. Specifically, we present a...

متن کامل

Joint Kernel-Based Supervised Hashing for Scalable Histopathological Image Analysis

Histopathology is crucial to diagnosis of cancer, yet its interpretation is tedious and challenging. To facilitate this procedure, content-based image retrieval methods have been developed as case-based reasoning tools. Recently, with the rapid growth of histopathological images, hashing-based retrieval approaches are gaining popularity due to their exceptional scalability. In this paper, we ex...

متن کامل

Supervised Composite Kernel Locality Preserving Projection Feature Extraction for Hyperspectral Image Classification

Locally preserving projection (LPP) does not take advantage of the spatial correlation of pixels in the image, and the pixels are considered as independent pieces of information. In this paper, a kernel based manifold learning feature extraction method which considers spatial relationship of neighboring pixels, called supervised composite kernel locality preserving projection (SCKLPP), is propo...

متن کامل

Performance Evaluation of SVM – RBF Kernel for Medical Image Classification

An approach for automatic classification of computed tomography (CT) medical images is presented in this paper. A vast amount of CT images are produced in modern hospitals due to advances of multi-slice Computed Tomography (CT) Scan which handles up to 64 slices per scan. So, an input image based automatic medical image retrieval system is now a necessity. In this paper, Coiflet wavelets are us...

متن کامل

Regularized RBF Networks for Hyperspectral Data Classification

In this communication, we analyze several regularized types of Radial Basis Function (RBF) Networks for crop classification using hyperspectral images. We compare the regularized RBF neural network with Support Vector Machines (SVM) using the RBF kernel, and AdaBoost Regularized (ABR) algorithm using RBF bases, in terms of accuracy and robustness. Several scenarios of increasing input space dim...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Journal of remote sensing

سال: 2022

ISSN: ['1007-4619', '2095-9494']

DOI: https://doi.org/10.11834/jrs.20220359