發(fā)布時間：2018-02-09 20:40

  本文關(guān)鍵詞： 超像素分割 區(qū)域比較 服飾提取 服飾屬性 圖像分割　出處：《西南交通大學》2016年碩士論文　論文類型：學位論文

【摘要】：隨著互聯(lián)網(wǎng)信息技術(shù)和電子商務(wù)產(chǎn)業(yè)的快速發(fā)展,線上購物成為一種方便、快捷、有吸引力的購物方式,得到了數(shù)以十億計的網(wǎng)絡(luò)用戶的關(guān)注。其中,服飾類商品在電商行業(yè)中具有十分重要的地位。通常,網(wǎng)絡(luò)用戶,尤其是女性消費者每天會花費幾個小時來瀏覽、搜索和選擇滿足她們需求的服飾。因此,基于計算機視覺的服飾搜索服務(wù)具有很大的商業(yè)價值。然而,服飾類購物圖像通常拍攝于自然戶外場景,且由時尚模特穿著來進行展示,這些特性使針對服飾類商品的視覺搜索成為一個極具挑戰(zhàn)性的課題。本文對服飾類商品圖像進行研究,從中提取出服飾來增強視覺搜索的質(zhì)量,主要內(nèi)容如下：第一,提出了一種結(jié)合姿勢檢測和區(qū)域比較的服飾提取算法,其使用超像素分割算法將圖像分成一系列區(qū)域,利用姿勢檢測定位服飾的大致區(qū)間,并將兩者結(jié)合確定服飾的種子區(qū)域。然后,本文結(jié)合位置信息和HSV顏色特征來計算區(qū)域間的相似度,利用加權(quán)平方誤差和來構(gòu)造目標函數(shù),將服飾分割問題轉(zhuǎn)化為通過迭代計算和重分配區(qū)域類別來最小化目標函數(shù)。實驗結(jié)果表明算法快速且具有魯棒性,能夠自動有效地進行服飾提取。第二,提出了基于衣物屬性和人體結(jié)構(gòu)的服飾提取優(yōu)化。對于區(qū)域比較算法來說,前景可能包含多個不連通部分,本文利用區(qū)域的大小和位置對其進行重要性建模。考慮到服飾的完整性,被服飾區(qū)域包圍的像素也應(yīng)該為服裝,因此我們將服飾內(nèi)部像素分配為前景類別。本文還提出了一種基于最大后驗概率的軀干模型,并利用軀干位置優(yōu)化沒有附著服飾的部位,如頭部和下肢。最后,采用GrabCut算法對服飾提取結(jié)果進行像素級別優(yōu)化。實驗結(jié)果表明該算法能有效地提升服飾提取性能,適用于廣泛的服飾圖像。
[Abstract]:With the rapid development of Internet information technology and e-commerce industry, online shopping has become a convenient, fast and attractive way of shopping, which has attracted the attention of several 1 billion network users. Clothing products play a very important role in the e-commerce industry. In general, Internet users, especially female consumers, spend several hours a day browsing, searching and selecting clothing that meets their needs. Clothing search services based on computer vision have great commercial value. However, clothing shopping images are usually taken in natural outdoor scenes and displayed by fashion models. These characteristics make the visual search for clothing products become a very challenging subject. This paper studies the image of clothing commodities, and extracts clothing to enhance the quality of visual search. The main contents are as follows: first, A dress extraction algorithm combining posture detection and region comparison is proposed, in which the image is divided into a series of regions by using the hyperpixel segmentation algorithm, and the approximate range of clothing is located by posture detection. Then, combining the position information and HSV color features to calculate the similarity between the regions, the weighted square error sum is used to construct the objective function. The problem of clothing segmentation is transformed to minimize the objective function by iterative computation and redistribution of region categories. Experimental results show that the algorithm is fast and robust, and can automatically and effectively extract clothing. Second, The clothing extraction optimization based on clothing attributes and human structure is proposed. For the region comparison algorithm, the foreground may contain multiple disconnected parts. This paper uses the size and location of the region to model its importance. Considering the integrity of the dress, the pixels surrounded by the dress area should also be garments. In this paper, we propose a trunk model based on the maximum posteriori probability, and use the trunk position to optimize the non-attached parts, such as the head and lower limbs. The GrabCut algorithm is used to optimize the pixel level of the clothing extraction results. The experimental results show that the algorithm can effectively improve the performance of clothing extraction and is suitable for a wide range of clothing images.
【學位授予單位】：西南交通大學
【學位級別】：碩士
【學位授予年份】：2016
【分類號】：TP391.41

【相似文獻】

相關(guān)期刊論文 前10條

1 唐浩;;蟻群算法的研究與展望[J];牡丹江教育學院學報;2009年06期

2 鄧小波;曹聰聰;龍倫海;康耀紅;;蟻群算法搜索熵研究[J];海南大學學報(自然科學版);2007年04期

3 張康;顧幸生;;全局組搜索優(yōu)化算法及其應(yīng)用研究[J];青島科技大學學報(自然科學版);2012年05期

4 李東曉;蔣珉;柴干;;蟻群算法優(yōu)化及其在高速公路緊急救援中的應(yīng)用[J];計算機技術(shù)與發(fā)展;2010年11期

5 _5文龍 ,黃，

本文編號：1498813