發(fā)布時(shí)間：2018-03-25 14:25

  本文選題：鞋底花紋開(kāi)集分類(lèi)　切入點(diǎn)：置信度　出處：《大連海事大學(xué)》2017年碩士論文

【摘要】：鞋底花紋是刑事偵查的重要物證之一,為了發(fā)揮鞋底花紋對(duì)案件偵破的重大作用,公安人員需要建立鞋印庫(kù)。當(dāng)新的鞋底花紋自動(dòng)添加到鞋印庫(kù)時(shí),會(huì)出現(xiàn)其可能屬于鞋印庫(kù)中的某個(gè)已知類(lèi)別也可能不屬于鞋印庫(kù)中任何一種類(lèi)別的情況。但是如果將現(xiàn)有效果很好的開(kāi)集分類(lèi)算法直接用于鞋底花紋,分類(lèi)器的性能會(huì)下降很多,因此需要設(shè)計(jì)鞋底花紋的開(kāi)集分類(lèi)算法�；�于此,本文提出了開(kāi)集鞋底花紋分類(lèi)算法研究,主要工作如下:1)給出了基于置信度的CSoftmax算法該算法針對(duì)目前Softmax分類(lèi)算法應(yīng)用于開(kāi)集場(chǎng)景時(shí)存在的問(wèn)題,通過(guò)引入置信度增大已知類(lèi)別和新類(lèi)別之間的概率分布差異,減小二者概率之間的重疊區(qū)域,以此提高開(kāi)集分類(lèi)算法的準(zhǔn)確率。實(shí)驗(yàn)結(jié)果表明:本文算法的性能指標(biāo)對(duì)于存在明顯隔離帶的鞋印數(shù)據(jù)集取得更好的效果,其中在包含9294幅鞋印圖像的數(shù)據(jù)集上 AUC 達(dá)到了 76.33%。2)給出了基于距離對(duì)比的DKNFST算法針對(duì)零空間下已知類(lèi)別和新類(lèi)別的距離特點(diǎn),本文不僅利用距離最近這一信息,還考慮距離最遠(yuǎn)的兩個(gè)類(lèi)別包含的有用信息,以此增大已知類(lèi)別和新類(lèi)別之間的分布差異。實(shí)驗(yàn)結(jié)果表明:本文算法在有明顯隔離帶的鞋印數(shù)據(jù)集上AUC達(dá)到了 74.16%。3)給出了基于流形一致性的MKNFST算法本文利用待檢測(cè)樣本在變換后的低維零空間,以及原始高維空間的流形一致特性,通過(guò)將待檢測(cè)樣本的兩種空間特性融合來(lái)設(shè)計(jì)分類(lèi)器,進(jìn)一步提高分類(lèi)的準(zhǔn)確率。實(shí)驗(yàn)結(jié)果表明:本文算法在有明顯隔離帶的鞋印數(shù)據(jù)集上AUC達(dá)到了83.77%。
[Abstract]:Sole pattern is one of the important material evidence in criminal investigation. In order to play the important role of sole pattern in the detection of cases, public security personnel need to establish shoe print bank. When the new sole pattern is automatically added to the shoe print store, It may or may not belong to any of the categories in the shoeprint library. However, if the existing open-set classification algorithm is used directly for the sole pattern, The performance of the classifier will decrease a lot, so it is necessary to design an open set classification algorithm for sole pattern. The main work of this paper is as follows: (1) this paper presents the CSoftmax algorithm based on confidence degree. Aiming at the problems existing in the application of Softmax classification algorithm to open set scene, the confidence degree is introduced to increase the difference of probability distribution between known and new categories. In order to improve the accuracy of the open set classification algorithm, the experimental results show that the performance index of this algorithm is better for the shoe print data set with obvious separation belt. In the data set containing 9294 shoeprint images, the AUC reaches 76.33.2) the distance characteristic of known and new categories in zero space is given by DKNFST algorithm based on distance contrast. This paper not only uses the nearest distance information, Considering also the useful information contained in the two categories most distant, The experimental results show that the AUC of the shoeprint data set with obvious straps is 74.16.3) the MKNFST algorithm based on manifold consistency is given in this paper. Detection of samples in the transformed low-dimensional zero space, And the manifold consistency of the original high-dimensional space, the classifier is designed by merging the two spatial characteristics of the sample to be detected. The experimental results show that the proposed algorithm achieves 83.77 AUC on the shoeprint data set with obvious separation band.
【學(xué)位授予單位】：大連海事大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類(lèi)號(hào)】：D918.91;TP391.41

【相似文獻(xiàn)】

相關(guān)會(huì)議論文 前10條

1 趙波;唐常杰;朱明放;魏大剛;左R，

本文編號(hào)：1663537