臺灣博碩士論文加值系統

本論文提出一種新的捲帶式封裝元件的計數方法，不同於傳統機械式計數機，此方法是藉由建立良好的拍攝環境讓攝影機來擷取一捲帶器的影像，接著把影像傳送到電腦來執行計數演算法，此方法能夠將複雜的計數過程推向低人力且自動化。
本論文注重的是軟體的設計，透過改良既有的計數演算法再搭配本論文設計的硬體架構使得計數過程更加簡易，此方法可將偵測結果顯示出來，由操作者肉眼判斷準確率，藉由重複計數(每次約8秒)，求取平均值以降低誤差。

This paper presents a new counting method for reeled components. Different from the traditional counting machine, this method creates a suitable shooting environment in which a camera can capture a reeled-component image and then transfer the image to the corresponding computer to execute the counting algorithm. This method simplifies the complex counting process, using automation and less human resources.
In particular, this paper focuses on the software design. Improving the existing counting algorithm and designing a novel hardware structure renders the counting process easier. The new method also displays detected results, and it allows the operator to judge their accuracy without assistance. The counting is repeated (approximately 8 s each) to determine the average, which reduces error.

摘要 i
Abstract ii
目錄 iii
圖目錄 v
表目錄 vii
第一章 緒論 1
1.1 研究背景 1
1.2 研究動機 1
1.3 文獻回顧 2
1.4 系統架構 3
1.5 論文架構 4
第二章 相關技術介紹 5
2.1 形態學影像處理 5
2.2 基本運算單元 5
2.3 灰階型態學 7
2.4 頂帽轉換與底帽轉換 8
2.5 雙線性內插法(Bilinear Interpolation) 8
2.6 攝影機功能 - zoom in 10
2.7 串列通訊（Serial communication） 10
2.8 多執行緒 (Multithreading) 11
第三章 元件計數演算法 13
3.1 演算法設計 13
3.2 演算法步驟 14
3.3 影像來源 14
3.4 影像分割 16
3.5 偵測元件層寬度 19
3.6 元件層軌跡與座標儲存管理 20
3.7 可見元件位置偵測 21
3.8 檢查可見區塊中的遺漏亮紋 22
3.9 被遮蔽元件位置估測 22
3.10 將結果與原圖重疊 23
第四章 實驗環境介紹與實驗成果 26
4.1 元件計數系統 26
4.2 使用者介面(GUI)設計 27
4.3 實驗環境簡介 29
4.4 實物攝影機 29
4.5 背光源 30
4.6 Arduino和伺服馬達 32
4.7 燈箱 33
4.8 電腦 34
4.9 演算法執行結果 35
4.10 樣本一 35
4.11 樣本二 38
4.12 樣本三 40
4.13 樣本四 42
4.14 樣本五 44
4.15 樣本六 46
第五章 結論與未來展望 48
5.1 結論 48
5.2 未來展望 49
參考文獻 50

[1]H.Y Lu, An optical system for tape and reel IC packages, NCHU Mas-ter Thesis, 2015
[2]K. C. Yow and R. Cipolla, "Feature-based human face detection," Image and vision computing, vol. 15, no. 9, pp. 713-735, 1997
[3]S.-H. Jeng, H. Y. M. Yao, C. C. Han, M. Y. Chern, and Y. T. Liu, "Facial feature detection using geometrical face model: An efficient approach", Pattern Recognit., vol. 31, no. 3, pp.273-282, 1998
[4]Jun-Wei Hsieh, Shih-Hao Yu, and Yung-Sheng Chen. "Morpholo-gy-based license plate detection from complex scenes". Proc. Int. Conf. Pattern Recog., vol. 3, pp. 176-180, 2002
[5]Ionescu B., Coquin D., Lambert P., V Buzuloiu, "Dynamic hand gesture recognition using the skeleton of the hand", EURASIP J Appl Signal Process 2005, pp.2101-2109, 2005
[6]Venkatalakshmi, B. and Thilagavathi, K., "Automatic red blood cell counting using hough transform", Information & Communication Technologies (ICT), 2013 IEEE Conference, pp.267-271, 2013
[7]Merad. D., Aziz. K.-E.and Thome. N., "Fast People Counting Using Head Detection from Skeleton Graph", Advanced Video and Signal Based Surveillance (AVSS), Seventh IEEE International Conference on Advanced Video and Signal Based Surveillance, pp. 233-240, 2010.
[8]Lee, Henry C., Robert Ramotowski, and R. E. Gaensslen, eds. Advances in fingerprint technology. CRC press, 2001
[9]Senior, Andrew W., and Anthony J. Robinson. "An off-line cursive handwriting recognition system." Pattern Analysis and Machine Intel-ligence, IEEE Transactions on 20.3 (1998): 309-321
[10]Hyung Jun Park and Seong Wook Han, "Detection of backlight images using chrominance", Proc. SPIE 82920J, 2012
[11]Youn, SeungGeun, YounAe Lee, and TaeHyung Park. "Automatic clas-sification of SMD packages using neural network." System Integration (SII), 2014 IEEE/SICE International Symposium on. IEEE
[12]Jackway, P. T. "Improved morphological top-hat." Electronics Let-ters 36.14 (2000): 1194-1195
[13]Jyoti Rawat, A. Singh, H.S. Bhadauria, I. kumar, Comparative Analysis of Segmentation Algorithms for Leukocyte Extraction in the Acute Lymphoblastiv Leukemia Images, 2014
[14]Hough. P., "Methods and means for recognizing complex patterns" Tech. Rep. 3069654, US Patent, 1962
[15]M. Pesaresi and J.A. Benediktsson, "A new approach for the morpho-logical segmentation of high-resolution satellite imagery", IEEE Trans. Geoscience and Remote Sensing, vol. 39, pp.309-320, 2001
[16]C.L Tseng, An optical system for tape and reel IC packages, NCHU Master Thesis, 2016
[17]SA, Yang. Improved Bilinear Interpolation Method for Image Fast Pro-cessing. In: 2014 7th International Conference on Intelligent Computa-tion Technology and Automation [online]. 2014 [cit. 2015-05-16]. DOI: 10.1109/icicta.2014.82
[18]https://www.google.com.tw/search?q=reeled+components&espv=2&rlz=1C1ASUC_enTW658TW658&biw=1920&bih=901&source=lnms&tbm=isch&sa=X&ved=0ahUKEwioiqT_ntzQAhUEJ5QKHUhtAdAQ_AUIBigB#imgrc=ekGO9hb2kqBx4M%3A
[19]http://uk.farnell.com/productimages/standard/en_GB/GEFULLREELRES-40.jpg