本文選題：關(guān)鍵點 + 深度卷積神經(jīng)網(wǎng)絡(luò)�。� 參考：《計算機應用》2017年11期

【摘要】：目前,同款或近似款式服裝檢索主要分為基于文本和基于內(nèi)容兩類�；谖谋舅惴ㄍ枰Ａ繕俗颖�,且存在人工主觀性帶來的標注缺失和標注差異等問題;基于內(nèi)容算法一般對服裝圖像的顏色、形狀、紋理提取特征,進行相似性度量,但難以應對背景顏色干擾,以及視角、姿態(tài)引起的服裝形變等問題。針對上述問題,提出一種基于關(guān)鍵點的服裝檢索方法。利用級聯(lián)深度卷積神經(jīng)網(wǎng)絡(luò)為基礎(chǔ),定位服裝關(guān)鍵點,融合關(guān)鍵點區(qū)域低層視覺信息以及整幅圖像的高層語義信息。對比傳統(tǒng)檢索方法,所提算法能有效處理視角、姿態(tài)引起的服裝形變和復雜背景的干擾;同時不需大量樣本標定,且對背景、形變魯棒。在Fashion Landmark數(shù)據(jù)集和BDAT-Clothes數(shù)據(jù)集上與常用算法進行對比實驗。實驗結(jié)果表明所提算法能有效提升檢索的查準率和查全率。
[Abstract]:At present, the same style or similar style clothing retrieval is divided into two categories: text-based and content-based. Text based algorithms often need a large number of tagged samples, and there are some problems such as missing annotation and annotation differences caused by artificial subjectivity. Based on content algorithm, the color, shape and texture features of clothing images are generally extracted, and the similarity is measured. However, it is difficult to deal with the background color interference, as well as the angle of view, posture caused by the deformation of clothing and so on. In order to solve the above problems, a key point based clothing retrieval method is proposed. Based on cascaded deep convolution neural network, the key points of clothing are located, and the low-level visual information of the key points and the high-level semantic information of the whole image are fused. Compared with the traditional retrieval method, the proposed algorithm can effectively deal with the disturbance of garment deformation and complex background caused by visual angle and posture, and it does not require a large number of samples to calibrate, and is robust to background and deformation. The experiments are carried out on Fashion Landmark dataset and BDAT-clothes dataset with common algorithms. Experimental results show that the proposed algorithm can effectively improve the precision and recall of retrieval.
【作者單位】： 江蘇省大數(shù)據(jù)分析技術(shù)重點實驗室(南京信息工程大學);
【基金】：國家自然科學基金資助項目(61622305,61502238,61532009) 江蘇省自然科學基金資助項目(BK20160040)~~
【分類號】：TP183;TP391.41

【相似文獻】

相關(guān)期刊論文 前1條

1 惠國保;李東波;;像素聚類改進二進制描述子魯棒性[J];中國圖象圖形學報;2014年04期

相關(guān)碩士學位論文 前1條

1 李坤;一種基于關(guān)鍵點和體素聯(lián)合的交互頭部三維重建方法[D];天津大學;2016年

，

本文編號：2116611