【摘要】：在木材行業(yè)中,最常用的識(shí)別木材的方法以視覺(jué)觀測(cè)為主,但是利用計(jì)算機(jī)進(jìn)行識(shí)別更為準(zhǔn)確。在圖像采集過(guò)程中由于環(huán)境以及采集設(shè)備的限制因素,導(dǎo)致人們所采集到的圖像并不理想,因此會(huì)使得提取的木材中的紋理信息丟失,這樣就會(huì)導(dǎo)致在利用圖像進(jìn)行木材圖像的識(shí)別時(shí)出現(xiàn)誤差。本文現(xiàn)有的圖像增強(qiáng)算法的基礎(chǔ)上,提出了基于權(quán)重系數(shù)的木材圖像增強(qiáng)算法,分析了低高頻、高低頻和高高頻等波段的小波變換的性能,從而有針對(duì)性的消除圖像中的混淆部分,提高圖像質(zhì)量。論文研究的主要內(nèi)容包括:1.本文重點(diǎn)介紹了直方圖均衡化算法、直方圖規(guī)定化算法、低通濾波算法、高通濾波算法和小波變換算法這五種傳統(tǒng)的圖像增強(qiáng)算法理論。2.在現(xiàn)有的圖像增強(qiáng)算法的基礎(chǔ)上,提出了基于權(quán)重系數(shù)的木材圖像增強(qiáng)算法,此方法主要是對(duì)圖像中混淆備份的定向篩選,即將整幅圖像分為L(zhǎng)L、LH、HL和HH四個(gè)不同的波段,對(duì)LL子帶進(jìn)行歸一化處理。并利用計(jì)算權(quán)重系數(shù)的方法獲得相似模塊,同時(shí)結(jié)合自適應(yīng)濾波模塊進(jìn)行混淆檢測(cè);對(duì)LH、HL和HH子帶采用局部方差法進(jìn)行混淆檢測(cè)。最后將其利用方向自適應(yīng)小波收縮進(jìn)行混淆消除,通過(guò)小波逆變換完成混淆消除恢復(fù)圖像。3.將基于權(quán)重系數(shù)的木材圖像增強(qiáng)算法與直方圖均衡化算法、直方圖規(guī)定化算法、低通濾波算法、高通濾波算法等方法進(jìn)行實(shí)驗(yàn)對(duì)比,并對(duì)所得實(shí)驗(yàn)結(jié)果進(jìn)行主觀和客觀分析。4.將基于權(quán)重系數(shù)的圖像增強(qiáng)算法應(yīng)用到木材圖像識(shí)別中,以榆木和榆木樹(shù)皮作為識(shí)別試樣,分別用基于權(quán)重系數(shù)的木材圖像增強(qiáng)算法和傳統(tǒng)的圖像增強(qiáng)對(duì)榆木木片和榆木樹(shù)皮圖像進(jìn)行預(yù)處理,并用BP神經(jīng)網(wǎng)絡(luò)對(duì)圖像進(jìn)行識(shí)別,且對(duì)其識(shí)別結(jié)果進(jìn)行分析和比較。
[Abstract]:In the timber industry, the most commonly used method of wood identification is visual observation, but it is more accurate to identify wood by computer. In the process of image acquisition, because of the limited factors of environment and acquisition equipment, the image collected by people is not ideal, so the texture information of extracted wood will be lost. This will lead to errors in the recognition of wood images using images. Based on the existing image enhancement algorithms, a wood image enhancement algorithm based on weight coefficient is proposed, and the performance of wavelet transform in low high frequency, high and low frequency and high frequency bands is analyzed. Thus the obfuscation part of the image is eliminated and the image quality is improved. The main contents of this paper are as follows: 1. This paper focuses on five traditional image enhancement algorithms: histogram equalization algorithm, histogram specification algorithm, low-pass filtering algorithm, high-pass filtering algorithm and wavelet transform algorithm. 2. On the basis of existing image enhancement algorithms, a wood image enhancement algorithm based on weight coefficient is proposed. This method is mainly used for directional filtering of obfuscation backups in images, that is to say, the whole image is divided into four different bands: LL,LH,HL and HH. The LL subbands are normalized. The similarity module is obtained by calculating the weight coefficient, and the aliasing detection is carried out by combining the adaptive filtering module, and the local variance method is used to detect the LH,HL and HH subbands. Finally, it uses directional adaptive wavelet shrinkage to eliminate confusion, and accomplishes the obfuscation elimination and restoration image by inverse wavelet transform. The wood image enhancement algorithm based on weight coefficient is compared with histogram equalization algorithm, histogram specification algorithm, low-pass filter algorithm, high-pass filtering algorithm and so on. The experimental results are analyzed subjectively and objectively. 4. The image enhancement algorithm based on weight coefficient is applied to wood image recognition. Elm and elm bark are used as the recognition samples. The wood image enhancement algorithm based on weight coefficient and the traditional image enhancement algorithm are used to preprocess the elm and elm bark images, and the BP neural network is used to identify the images, and the recognition results are analyzed and compared.
【學(xué)位授予單位】：內(nèi)蒙古農(nóng)業(yè)大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類(lèi)號(hào)】：TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 江華麗;王平;;神經(jīng)網(wǎng)絡(luò)和小波變換融合算法的去噪研究[J];計(jì)算機(jī)系統(tǒng)應(yīng)用;2016年05期

2 段益群;曾輝;卓輝;;小波分解和重構(gòu)算法在數(shù)字圖像上的應(yīng)用[J];機(jī)械工程與自動(dòng)化;2016年03期

3 肖化超;周詮;張建華;;遙感衛(wèi)星在軌機(jī)場(chǎng)變化檢測(cè)方法[J];測(cè)繪通報(bào);2015年01期

4 多化豫;高峰;李福勝;魏漢夫;張欣宏;;基于圖像處理的木片與樹(shù)皮的新識(shí)別參數(shù)研究[J];西北林學(xué)院學(xué)報(bào);2015年01期

5 朱佳;汪杭軍;;基于Graph Cuts的木材掃描電鏡圖像特征提取方法[J];林業(yè)科學(xué);2014年04期

6 陳莉;;基于小波變換的圖像增強(qiáng)算法[J];陜西理工學(xué)院學(xué)報(bào)(自然科學(xué)版);2014年01期

7 孫書(shū)冬;甘雪菲;霍麗平;周旭;;基于Visual Basic的木材識(shí)別系統(tǒng)[J];木材工業(yè);2013年05期

8 孫亮;;計(jì)算機(jī)智能化圖像識(shí)別技術(shù)的理論性突破[J];數(shù)字技術(shù)與應(yīng)用;2013年06期

9 李觀石;劉波;陸藩藩;宋法奇;;基于MMS街景的導(dǎo)航數(shù)據(jù)采集方法研究[J];現(xiàn)代測(cè)繪;2013年01期

10 扈佃海;呂緒良;文劉強(qiáng);;一種改進(jìn)的直方圖均衡化圖像增強(qiáng)方法[J];光電技術(shù)應(yīng)用;2012年03期

相關(guān)碩士學(xué)位論文 前4條

1 吳禹權(quán);數(shù)據(jù)融合技術(shù)在汽車(chē)識(shí)別中的應(yīng)用研究[D];華南理工大學(xué);2012年

2 周凌翱;改進(jìn)BP神經(jīng)網(wǎng)絡(luò)在模式識(shí)別中的應(yīng)用及研究[D];南京理工大學(xué);2010年

3 須岳林;基于BP神經(jīng)網(wǎng)絡(luò)的印刷體字符識(shí)別系統(tǒng)的研究[D];南京航空航天大學(xué);2006年

4 方彩婷;基于BP神經(jīng)網(wǎng)絡(luò)的圖像識(shí)別與跟蹤研究[D];西安電子科技大學(xué);2006年

，

本文編號(hào)：2328754