民生議題中有大部份十分適合利用數位影像處理來解決，其中像是避障及重疊指紋分離就是十分適切，所以本論文基於創新影像處理演算法解決避障及重疊指紋分離此兩個議題。第一個議題是避障，根據研究資料顯示，目前全台灣約有5萬6 名視障人口，有許多視障人士需要依賴導盲杖觸碰地面或物體,判斷前方是否有可以行走的區域,碰觸不到的地方，只能由聽覺去評估周遭環境或用嗅覺判斷所身處的位置。或者是由導盲犬引導視障人士避障，但是不是每一位視障人士都能夠輕易和導盲犬配對成功並取得,而且導盲犬的訓練需要時間，所以他們往往需要等待很長一段時間，在使用的時間上,也不會比相關輔助器具長久。為了使視障人士能夠有效的了解周遭環境,利用電腦視覺與導盲杖相互配合就能解決這方面的問題，因此如何有效地偵測障礙物,是本研究的重要課題。本研究提出使用深度資訊，協助視障人士避開障礙物，當他們在一個陌生的環境中移動障礙物檢測方法。該系統由三個部分組成：場景偵測，障礙物偵測和聲音警示。本項研究提出了一種新的方法來刪除克服過分割問題的地平面。本系統通過去除邊緣以及用於使用所連接的設備的方法（CCM）的區域生長方法的初始種子位置的問題解決了過分割的問題。本系統可檢測的靜態和動態的障礙，功能強大，高效能，實驗結果證明本系統既強韌又方便。
第二個議題是重疊指紋分離，指紋被當作是生物識別的一個重要工具，而犯罪現場的重疊指紋辨識是警方辦案的困擾。因重疊與未重疊指紋邊界區域的方向場計算，易受重疊指紋區域影響，導致錯誤的指紋分離與辨識，本論文提出重疊指紋自動分離系統及改良式指紋方向場增強演算法以利辨識。首先，進行重疊與非重疊區域的判別。利用重疊區域有兩個方向場且指紋山脊點數較未重疊區域多的特性進行初步分離。核心點區域與重疊區域有類似特性，容易被誤判為重疊區域。再利用核心點的偵測，修正未重疊區域。最後，利用指紋輪廓明顯與否區分兩枚未重疊指紋區域。進行兩枚指紋的分離與辨識。在重疊與未重疊指紋邊界區域的方向場計算容易產生錯誤，本文提出遞迴式的方向場演算法，再結合限制鬆弛標籤演算法分配方向場，最後用Gabor-filter進行強化，再由Verifinger進行辨識。

Most of the livelihood issues are very suitable for digit image processing to solve. The Livelihood issues are such as obstacle avoidance and overlapping fingerprint separation is very relevant, so this paper based on an innovative image processing algorithms to solve the obstacle avoidance and overlapping fingerprint separation issues. The first issue of this study proposes an obstacle detection method that uses depth information to allow visually impaired to avoid obstacles when they move in an unfamiliar environment. According to new statistics, there are 285 million visually impaired people relying on the guide cane or guide dogs to move around freely in the world. However, not every visually impaired person can easily pair successfully with guide dogs and there is often a long wait for an animal. The system is composed of three parts: scene detection, obstacle detection and a vocal announcement. This study proposes a new method to remove the ground plane that overcomes the over-segmentation problem. This system addresses the over-segmentation problem by removing the edge and the initial seed position problem for the region growth method using the Connected Component Method (CCM). This system can detect static and dynamic obstacles. The system is simple, robust and efficient. The experimental results show that the proposed system is both robust and convenient. 
The second issue of this study presents an improved fingerprint recognition system for overlapping fingerprint of two fingers. The developed system can automatically and precisely separate an overlapping fingerprint into two areas, an overlapping area and a non-overlapping area, by analyzing their orientation fields and complexity. A method being able to remove a misjudging condition from the overlapping area is also proposed in this paper. Moreover, a recursive correction algorithm and a constrained relaxation labeling algorithms are applied to separate two fingerprints from the determined overlapping fingerprint area, and the Gabor filter is applied to enhance figure quality of the two separated fingerprints. After that, the VeriFinger 6.2 SDK is used to identify the fingerprints. In the experiments, the fingerprints in the two databases, Receiver Operating Characteristic (ROC) and Cumulative Match Characteristic (CMC), are used to examine the proposed fingerprint recognition system.

Table of Contents
TABLE OF CONTENTS	V
LIST OF FIGURES	VII
LIST OF TABLES	XI
CHAPTER 1	INTRODUCTION	1
1.1.	MOTIVATION	1
1.2.	RESEARCH OBJECTIVE	2
1.3.	ORGANIZATION OF DISSERTATION	2
CHAPTER 2	LITERATURE REVIEWS	4
2.1.	OBSTACLE AVOIDANCE	4
2.2.	OVERLAPPING FINGERPRINT	6
CHAPTER 3	OBSTACLE AVOIDANCE SYSTEM	8
3.1.	SYSTEM ARCHITECTURE	8
3.2.	NOISE REDUCTION	9
3.3.	GROUND HEIGHT DETECTION	10
3.4.	REMOVAL OF THE EDGE	15
3.5.	THE DETECTION OF DESCENDING STAIRS	17
3.6.	REMOVAL OF THE GROUND	17
3.7.	LABELING	19
3.8.	THE DETECTION OF RISING STAIRS	22
3.9.	THE LABELING OF OBJECTS AND INFORMING THE USER	23
CHAPTER 4	EXPERIMENTAL RESULTS OF OBSTACLE AVOIDANCE SYSTEM	24
4.1.	SYSTEM TESTING IN A SIMPLE ENVIRONMENT	25
4.2.	AN INDOOR ENVIRONMENT UNDER SUFFICIENT LIGHT	25
4.3.	AN INDOOR ENVIRONMENT UNDER INSUFFICIENT LIGHT	26
4.4.	SYSTEM TESTING IN A COMPLICATED ENVIRONMENT	27
4.5.	AN INDOOR ENVIRONMENT UNDER SUFFICIENT LIGHT	28
4.6.	AN INDOOR ENVIRONMENT UNDER INSUFFICIENT LIGHT	29
4.7.	THE CONFUSION MATRIX FOR EXPERIMENT RESULTS	30
4.8.	THE DETECTION OF STATIC AND DYNAMIC OBSTACLES	30
4.9.	THE EVALUATION OF THE SYSTEM BY BLIND AND BLINDFOLDED PARTICIPANTS	31
CHAPTER 5	AUTOMATIC SEPARATION OF OVERLAPPED FINGERPRINTS	34
5.1.	SYSTEM FLOW	34
5.2.	PREPROCESSING OF IMAGE	36
5.3.	OVERLAPPING AREA DETERMINATION	38
5.3.1.	INITIAL OVERLAPPING AREA DETERMINATION	38
5.3.2.	CORE POINT DETECTION AND MISJUDGMENT EXCLUSION	40
5.3.3.	THE OVERLAPPING FINGERPRINT AREA SEGMENTATION	42
5.4.	IMPROVED ENHANCEMENT OF FINGERPRINT ORIENTATION FIELD	46
5.4.1.	THE FINGERPRINT DIRECTION	47
5.4.2.	MODIFIED FOURIER ORIENTATION FIELD ESTABLISHMENT	47
5.4.3.	CONSTRAINED RELAXATION LABELING	49
5.4.4.	GABOR-FILTER FOR FINGERPRINT ENHANCEMENT	49
CHAPTER 6	AUTOMATIC SEPARATION EXPERIMENTS OF OVERLAPPED FINGERPRINTS	51
6.1.	THE INTRODUCTION OF FINGERPRINT DATABASE	51
6.2.	EXPERIMENT RESULTS OF ROC AND CMC	52
6.3.	ESTIMATION OF IMPROVED FOURIER ORIENTATION FIELD	59
6.4.	COMPARISON OF DIFFERENT ANGLES AND DIFFERENT PROPORTIONS OF OVERLAPPING	60
CHAPTER 7	SUMMARY AND FUTURE WORK	63

LIST OF FIGURES
FIGURE 1 THE SYSTEM FLOWCHART.	8
FIGURE 2 NOISE REMOVAL.	10
FIGURE 3 THE RELATIONSHIP BETWEEN THE DEPTH IMAGE AND THE V-DISPARITY.	11
FIGURE 4 A SCHEMATIC DIAGRAM OF THE V DISPARITY MAP.	11
FIGURE 5 (A) THE DEPTH IMAGE WITH NOISE REMOVED AND (B) THE V DISPARITY MAP IMAGE.	12
FIGURE 6 THE GROUND CURVE IN V DISPARITY MAP.	13
FIGURE 7 THE SCENE WITHOUT PEOPLE.	14
FIGURE 8 THE SCENE WITH PEOPLE.	14
FIGURE 9 NO OFFSET.	15
FIGURE 10 OFFSET VALUE = 20.	15
FIGURE 11 THE RESULT OF THE OFFSET.	15
FIGURE 12 REMOVAL OF THE EDGE.	16
FIGURE 13 THE RESULTS FOR THE DETECTION OF DESCENDING STAIRS.	17
FIGURE 14 REMOVAL OF THE GROUND.	18
FIGURE 15 LABELING.	19
FIGURE 16 THE MASK FOR THE INITIAL SEED.	21
FIGURE 17 THE RESULTS FOR OBSTACLE DETECTION.	22
FIGURE 18 THE DETECTION OF RISING STAIRS.	22
FIGURE 19 THE RESULT OF LABELING.	23
FIGURE 20 THE DETECTION OF AN OBSTACLE INDOORS UNDER SUFFICIENT LIGHT.	26
FIGURE 21 THE DETECTION OF AN INDOOR OBSTACLE UNDER INSUFFICIENT LIGHT.	26
FIGURE 22 THE STRUCTURE OF THE STAIR.	27
FIGURE 23 THE DETECTION OF AN OBSTACLE INDOORS UNDER SUFFICIENT LIGHT.	28
FIGURE 24 THE DETECTION OF AN OBSTACLE INDOORS UNDER INSUFFICIENT LIGHT.	29
FIGURE 25 THE DETECTION OF STATIC AND DYNAMIC OBSTACLES.	31
FIGURE 26 BLIND AND BLINDFOLDED PARTICIPANTS.	31
FIGURE 27 THE EXPERIMENTAL ENVIRONMENT.	32
FIGURE 28 THE STATISTICAL DATA OF EXPERIMENT.	32
FIGURE 29 THE DISTRIBUTION OF THE EXPERIMENTAL DATA.	33
FIGURE 30 THE OVERLAPPING FINGERPRINT AND SEGMENTATION AREA (A) THE OVERLAPPING FINGERPRINT (B) THE NON-OVERLAPPING AREA OF FINGERPRINT #1 (C) THE NON-OVERLAPPING AREA OF FINGERPRINT #2 (D) THE OVERLAPPING AREA OF FINGERPRINT #1 AND FINGERPRINT #2	35
FIGURE 31 FLOWCHART OF AUTOMATED FINGERPRINT IDENTIFICATION SYSTEMS (AFIS)	35
FIGURE 32 FLOWCHART OF FINGERPRINT PREPROCESSING (A) ORIGINAL OVERLAPPING FINGERPRINT IMAGE (B) REMOVAL OF BACKGROUND OF THE OVERLAPPING FINGERPRINT IMAGE [12] (C) BINARIZATION (D) RESULTS OF ENHANCEMENT IMAGE OF THE OVERLAPPING FINGERPRINT	36
FIGURE 33 FOREGROUND OF FINGERPRINT	37
FIGURE 34 OTSU BINARIZATION	37
FIGURE 35 FLOWCHART OF REGION DECISION	38
FIGURE 36 THE FINGERPRINT IMAGE AND THE INITIAL OVERLAPPING AREA (A) ORIGINAL OVERLAPPING FINGERPRINT IMAGE (B) MAKE OVERLAPPING AREA OF FINGERPRINT IMAGE (C) OVERLAPPING AREA (D) NON-OVERLAPPING AREA	39
FIGURE 37 CORRECT THE INITIAL OVERLAPPING AREA BY MORPHOLOGY. (A) OVERLAPPING AREA (B) OVERLAPPING AREA BY MORPHOLOGY (C) NON-OVERLAPPING AREA (D) NON-OVERLAPPING AREA BY MORPHOLOGY	39
FIGURE 38 THE CHARACTERISTIC ORIENTATION FIELD OF CORE POINT [16]. (A) CORE POINT OF FINGERPRINT (B) RING-TYPE ORIENTATION FIELD OF CORE POINT	41
FIGURE 39 THE MASK OF SEARCHING FINGERPRINT CORE	41
FIGURE 40 THE PROCESS OF MISJUDGMENT EXCLUSION (A) ORIGINAL OVERLAPPING FINGERPRINT IMAGE (B) CORE OF FINGERPRINT BUT NOT IN OA (C) THE SCHEMATIC DIAGRAM OF MISJUDGMENT AREA (D) THE SCHEMATIC DIAGRAM OF MISJUDGMENT AREA EXCLUSION (E) RESULT OF ELIMINATION PROCEDURE	42
FIGURE 41 CASE OF EASY TO DISTINGUISH THE TWO FINGERPRINTS BY OBVIOUS CONTOUR	43
FIGURE 42 CASE OF EASY TO DISTINGUISH THE TWO FINGERPRINTS BY UNOBVIOUS CONTOUR	43
FIGURE 43 FORWARD AND REVERSE SEARCH ALONG FINGERPRINT CONTOUR. (A) FORWARD SEARCH ALONG FINGERPRINT CONTOUR. (B) REVERSE SEARCH ALONG FINGERPRINT CONTOUR.	43
FIGURE 44 SCHEMATIC DIAGRAMS OF TWO SEGMENTATION METHODS. (A) ORIGINAL OVERLAPPING FINGERPRINT IMAGE (B) ONE SEGMENTATION METHOD (C) THE OTHER ONE SEGMENTATION METHOD (D) OVERLAPPING AREA	45
FIGURE 45 OBJECT A IS DIVIDED INTO 16×16 NON-OVERLAPPING BLOCKS	45
FIGURE 46 ANY BLOCK OF OBJECT A SEARCHES IN OBJECT B IN 80×80 RANGE.	45
FIGURE 47 THE NON-OVERLAPPING AREA SEGMENTATION (A) ORIGINAL OVERLAPPING FINGERPRINT IMAGE (B) NOA OF THE FINGERPRINT (C) NOA AFTER EROSION (D) CLASSIFICATION (E) NOA OF FINGERPRINT 1 (F) NOA OF FINGERPRINT 2	46
FIGURE 48 FLOWCHART OF THE ENHANCED FINGERPRINT DIRECTION	47
FIGURE 49 THE LOCAL ORIENTATION FIELD IS AFFECTED BY THE OVERLAPPING AREA AND IT CAUSES MISJUDGMENT. (A) ORIGINAL OVERLAPPING FINGERPRINT IMAGE (B) MISJUDGMENT CASE (C) THE LOCAL ORIENTATION FIELD IMAGE.	48
FIGURE 50 LOCAL DIRECTION MISJUDGMENT AND CORRECTED LOCAL ORIENTATION FIELD. (A) THE ORIENTATION FIELD IMAGE OF MISJUDGMENT (B) MISJUDGMENT (C) THE ORIENTATION FIELD IMAGE OF CORRECTED LOCAL ORIENTATION FIELD (D) CORRECTED LOCAL ORIENTATION FIELD	48
FIGURE 51 THE RESULTS OF THE GRADUAL MOVEMENT REDUCE EFFECT CAUSED BY THE OVERLAPPING AREA. (A)10% (B) 20% (C) 30% (D) 40%	49
FIGURE 52 ENHANCEMENT PROCESSING OF GABOR-FILTER.	50
FIGURE 53 AN EXAMPLE OF THE NATURAL OVERLAPPING FINGERPRINT (A) EXAMPLE 1 (B) EXAMPLE 2	52
FIGURE 54 AN EXAMPLE OF THE SYNTHETIC OVERLAPPING FINGERPRINT. (A) EXAMPLE 1 (B) EXAMPLE 2	52
FIGURE 55 ROC OF THE SYNTHETIC OVERLAPPING FINGERPRINT	53
FIGURE 56 ROC OF THE NATURAL OVERLAPPING FINGERPRINT	54
FIGURE 57 CMC OF THE SYNTHETIC OVERLAPPING FINGERPRINT	54
FIGURE 58 CMC OF THE NATURAL OVERLAPPING FINGERPRINT	55
FIGURE 59 ENHANCEMENT AFTER AUTOMATIC FINGERPRINT AREA SEGMENTATION	58
FIGURE 60 AN EXAMPLE OF THE AUTOMATIC LABEL EXPERIMENT FAILURE. (A) ORIGINAL OVERLAPPING FINGERPRINT IMAGE	58
FIGURE 61 ROC OF IMPROVED FOURIER ORIENTATION FIELD	59
FIGURE 62 AN EXAMPLE OF IMPROVED FOURIER ORIENTATION FIELD. (A) ORIGINAL OVERLAPPING FINGERPRINT IMAGE (B) THE ERROR ORIENTATION FIELD (C) THE CORRECT ORIENTATION FIELD (D) ORIGINAL OVERLAPPING FINGERPRINT IMAGE (E) THE ERROR (F) THE CORRECT (G) THE ERROR SEGMENTED FINGERPRINT IMAGE (H) THE CORRECT SEGMENTED FINGERPRINT IMAGE (I) THE ERROR SEGMENTED FINGERPRINT IMAGE (J) THE CORRECT SEGMENTED FINGERPRINT IMAGE	60
FIGURE 63 THE SCHEMATIC DIAGRAM OF OVERLAPPING PERCENTAGE. (A) ORIGINAL FINGERPRINT A IMAGE (B) ORIGINAL FINGERPRINT B IMAGE (C) FINGERPRINT A’S AREA (D) FINGERPRINT B’S AREA (E) THE OVERLAPPING AREA C OF FINGERPRINT A’S AREA AND FINGERPRINT B’S AREA	61
FIGURE 64 SCHEMATIC DIAGRAM OF SYNTHESIS OF OVERLAPPING FINGERPRINT. (A) 20% OA FOR EXAMPLE 1 (B) 40% OA FOR EXAMPLE 1 (C) 60% OA FOR EXAMPLE 1 (D) 80% OA FOR EXAMPLE 1 (E) 20% OA FOR EXAMPLE 2 (F) 40% OA FOR EXAMPLE 2 (G) 60% OA FOR EXAMPLE 2 (H) 80% OA FOR EXAMPLE 2	62
LIST OF TABLES
TABLE 1 THE SUCCESS RATE AND THE FAILURE RATE FOR THE DETECTION OF OBSTACLES.	26
TABLE 2 THE SUCCESS RATE AND THE FAILURE RATE FOR OBSTACLE DETECTION.	27
TABLE 3 THE SUCCESS RATE AND THE FAILURE RATE FOR OBSTACLE DETECTION.	28
TABLE 4 THE SUCCESS RATE AND THE FAILURE RATE FOR OBSTACLE DETECTION.	29
TABLE 5 THE SUCCESS RATE AND FAILURE RATE FOR DETECTION OF DESCENDING STAIRS.	30
TABLE 6 THE CONFUSION MATRIX FOR THE INDOOR EXPERIMENT RESULTS.	30
TABLE 7. CORRECT RATE COMPARISON OF AUTOMATIC AND MANUAL OF THE SYNTHETIC OVERLAPPING FINGERPRINTS	56
TABLE 8. CORRECT RATE COMPARISON OF AUTOMATIC AND MANUAL OF THE NATURAL OVERLAPPING FINGERPRINTS	56
TABLE 9. THE EXPERIMENTAL RESULTS UNDER DIFFERENT ANGLES AND DIFFERENT PROPORTIONS OF OVERLAPPING FINGERPRINTS	57

[1]	International Agency for Prevention of Blindness: http://www.iapb.org/
[2]	Dakopoulos, D., Bourbakis, N.G., “Wearable Obstacle Avoidance Electronic Travel Aids for Blind: A Survey.  IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews,” Volume: 40, Issue: 1, 2010, pp. 25 – 35
[3]	Ma G. et al., “A Real-Time Rear View Camera Based Obstacle Detection,” 12th IEEE International Conference on Intelligent Transportation Systems, St. Louis, MO, 4-7 Oct. 2009, pp. 1-6. 
[4]	Yankun Zhang, Hong Chuyang, Weyrich N. “A single camera based rear obstacle detection system” Intelligent Vehicles Symposium, 2011 IEEE, Baden-Baden, 5-9 June 2011, pp.485-490. 
[5]	Chen L., Guo B.L., Sun W. “Obstacle Detection System for Visually Impaired People Based on Stereo Visio,” 2010 Fourth International Conference on Genetic and Evolutionary Computing, 13-15 Dec. 2010, pp.723-726. 
[6]	Ying Jie, Song Yanbin, “Obstacle Detection of a Novel Travel Aid for Visual Impaired People,” 2012 4th International Conference on Intelligent Human-Machine Systems and Cybernetics (IHMSC), 26-27 Aug. 2012, pp. 362-364.
[7]	Luis A. Guerrero, Francisco Vasquez, Sergio F. Ochoa, “An Indoor Navigation System for the Visually Impaired. Sensors 2012, 12(6), pp.8236-8258
[8]	Zhang Min., et al.  An Obstacle Detection Algorithm Based on U-V Disparity Map Analysis. 2010 IEEE International Conference on Information Theory and Information Security (ICITIS), 17-19 Dec. 2010, pp. 763-766.
[9]	Yuan Gao et al.  Obstacle Detection with 3D Camera Using U-V Disparity. 2011 7th International Workshop on Systems, Signal Processing and their Applications (WOSSPA), Tipaza , 9-11 May 2011, pp. 239-242. 
[10]	Jinwook Choi et al.  Rear Obstacle Detection System Based on Depth From Kinect. 2012 15th International IEEE Conference on Intelligent Transportation Systems (ITSC), Anchorage, AK, 16-19 Sept. 2012, pp.98-101.
[11]	Donghun Kim, Kwangtaek Kim, Sangyoun Lee, Stereo Camera Based Virtual Cane System with Identifiable Distance Tactile Feedback for the Blind. Sensors 2014, 14(6), pp.10412-10431
[12]	Alberto Rodriguez, J. Javier Yebes, Pablo F. Alcantarilla, Luis M. Bergasa, Javier Almazan, Andres Cela, Assisting the Visually Impaired: Obstacle Detection and Warning System by Acoustic Feedback. Sensors 2012, 12(12), pp.17476-17496, 
[13]	Brock, M., Kristensson, “Supporting blind navigation using depth sensing and sonification,” In Adjunct Proceedings of the 2013 ACM International Joint Conference on Pervasive and Ubiquitous Computing (Ubicomp 2013). ACM Press: pp.255-258. 
[14]	Edwards, N., Rosenthal, J., Moberly, D., Lindsay, J.,
Blair, K., Krishna, S., McDaniel, T., Panchanathan, S. “A pragmatic approach to the design
and implementation of a vibrotactile belt and its applications,” In Proc. HAVE 2009, IEEE Press (2009), pp.13-18. 
[15]	vOICe’s Glasses for the Blind: http://www.artificialvision.com 
[16]	Mann, S., Huang, J., Janzen, R., “Blind Navigation with a Wearable Range Camera and Vibrotactile Helmet,” Proceedings of 19th ACM International Conference son Multimedia, pp. 1325–1328. ACM, New York (2011) 
[17]	C. H. Lee, Y. C. Su, L. G. Chen, “An intelligent depth-based obstacle detection system for visually-impaired aid applications. WIAMIS, May 23-25 2012, pp. 1–4. 
[18]	Sales, D. O., Correa, D., Osorio, F. S. & Wolf, D. F., ”3D Vision-Based Autonomous Navigation System Using ANN and Kinect Sensor,” in Chrisina Jayne, Shigang Yue & Lazaros S. Iliadis, ed., 'EANN', Volume 311, Springer 2012, pp. 305-314 .
[19]	C. Zheng, R. Green, “Feature Recognition and Obstacle Detection for Drive Assistance in Indoor Environments,” University of Canterbury, Christchurch, New Zealand, 29, Nov-1 Dec 2011.
[20]	Suzuki S, Abe K., “Topological structural analysis of digitized binary images by border following,” (J). Computer Vision, Graphics, and Image Processing, Volume 30, Issue 1, April 1985, pp.32-46.
[21]	R. Adams, L. Bischof, “Seeded region growing, ”IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 16, no. 6, June, 1994, pp. 641-647. 
[22]	Zhencheng Hu, Francisco Lamosa, Keiichi Uchimura, “A Complete U-V-Disparity Study for Stereovision Based 3D Driving Environment Analysis,” 13-16 June 2005, pp. 204-211
[23]	RO Duda, PE Hart, “Use of the Hough Transformation To Detect Lines and Curves in Pictures,” Communications of the ACM, Volume 15 Issue 1, Jan. 1972, pp. 11-15. 
[24]	Zheng, Chunhui, Richard Green, “Vision-based autonomous navigation in indoor environments,” Image and Vision Computing New Zealand (IVCNZ), 25th International Conference of. IEEE. 8-9 Nov. 2010, pp.1-7
[25]	Soquet, Nicolas, Didier Aubert, Nicolas Hautiere, “Road segmentation supervised by an extended v-disparity algorithm for autonomous navigation. Intelligent Vehicles Symposium, IEEE, 2007, pp.160-165.
[26]	Marques, Oge et al. “An Attention-driven Model for Grouping Similar Images with Image Retrieval Applications,” EURASIP Journal on Applied Signal Processing Volume 2007 Issue 1, 1 January 2007, p.116. 
[27]	Wang, Shuihua et al., “RGB-D image-based Detection of Stairs, Pedestrian Crosswalks and Traffic Signs,” Journal of Visual Communication and Image Representation Volume 25, Issue 2, February 2014, pp. 263–272. doi: 10.1016/j.jvcir.2013.11.005
[28]	Rodriguez, Alberto et al., “Obstacle Avoidance System for Assisting Visually Impaired People. In Proceedings of the IEEE Intelligent Vehicles Symposium Workshops, Madrid, Spain. 2012, pp.1-6.
[29]	Fazli, Saeid, Mohammadi D, Hajar, Moallem, Payman, “An Advanced Stereo Vision Based Obstacle Detection with a Robust Shadow Removal Technique,” World Academy of Science, Engineering & Technology, Jul 2010, Issue 43, p.699.
[30]	Andreas Hub, Tim Hartter, Thomas Ertl, “Interactive tracking of movable objects for the blind on the basis of environment models and perception-oriented object recognition methods,” Assets '06 In Proceedings of the 8th international ACM SIGACCESS conference on Computers and accessibility. Oct 23-25 2006, pp. 111-118.
[31]	Piotr Skulimowski, Paweł Strumiłło, “Obstacle Localization In 3d Scenes From Stereoscopic Sequences, ”15th European Signal Processing Conference (EUSIPCO 2007), Poznan, Poland, September 3-7, 2007, pp. 2095-2099.
[32]	Ching-Tang Hsieh, Wei-Ming Lai, Cheng-Hsiang Yeh, Hsieh-Chang Huang, “An Obstacle Detection System Using Depth Information and Region Growing for Blind.,” Research Notes in Information Science (RNIS), Volume14, June 18 - 20, 2013, pp. 465-470.
[33]	Aladren A, Lopez-Nicolas G , Puig, L., Guerrero J.J., “Navigation Assistance for the Visually Impaired Using RGB-D Sensor With Range Expansion, ” Systems Journal, IEEE Issue: 99 May 22 2014,  pp.1–11. 
[34]	McAndrew, Introduction To Digital Image Processing With Matlab. Cengage Learning: Asia Edition, 2010, pp.267-302.
[35]	Hongshan Yu, Jiang Zhu, Yaonan Wang, Wenyan Jia, Mingui Sun, Yandong Tang, “Obstacle Classification and 3D Measurement in Unstructured Environments Based on ToF Cameras,” Sensors (Basel). 2014 Jun, 14(6) pp. 10753-10782. 
[36]	Alexy Bhowmick, Saurabh Prakash, Rukmani Bhagat, Vijay Prasad, Shyamanta M. Hazarika, “IntelliNavi: Navigation for Blind Based on Kinect and Machine Learning,” Multi-disciplinary Trends in Artificial Intelligence Lecture Notes in Computer Science Volume 8875, 2014, pp. 172-183.
[37]	Qing Lin, Youngjoon Han, “A Context-Aware-Based Audio Guidance System for Blind People Using a Multimodal Profile Model,” Sensors 2014, 14(10), pp.18670-18700. 
[38]	Tamkang University: Available online: http://www.tku.edu.tw
[39]	Leap motion: Available online: https://www.leapmotion.com/
[40]	Hokuyo: Available online: http://www.acroname.com/products/index_Hokuyo.html 
[41]	IR Distance Sensor: Available online: http://www.acroname.com/articles/sharp.html 
[42]	TTS: http://msdn.microsoft.com/en-us/library/ms723627(v=vs.85).aspx 
[43]	IntelR RealSense™: https://software.intel.com/en-us/realsense/home 
[44]	H. Kekre1 and V. Bharadi, “Fingerprint Orientation Field Estimation Algorithm Based on Optimized Neighborhood Averaging,” in Second International Conference on Emerging Trends in Engineering and Technology.( ICETET), 2009.
[45]	C. Raffaele, “Fast and Accurate Fingerprint Indexing Based on Ridge Orientation and Frequency,” in IEEE Trans. on system, vol. 41, no. 6, 2011.
[46]	C.Sharat, N Alexander, and G Venu, “Fingerprint enhancement using STFT analysis”, Pattern Recognition, 2007, pp. 198-211.
[47]	C. Watson and C. Wilson, “NIST Special Database 4, Fingerprint Database", National Institute of Standards and Technology, Mar. 1992.
[48]	L. Hong, Y. Wan, and A. K. Jain, “Fingerprint image enhancement: Algorithm and performance evaluation,” IEEE Trans. Pattern Anal.Mach. Intell., vol. 20, no. 8, Aug. 1998, pp. 777–789.
[49]	A. K. Jain and J. Feng, “Latent palmprint matching,” IEEE Trans.Pattern Anal. Mach. Intell., vol. 31, no. 6, Jun. 2009, pp. 1032–1047.
[50]	X. Fan, D. Liang, and L. Zhao, “A scheme for separating overlapped fingerprints based on partition mask,” (in Chinese) Comput. Eng. Applicat., vol. 40, no. 2, 2004, pp. 80–81.
[51]	F. Chen, J. Feng, A. K. Jain, J. Zhou, and J. Zhang, “Separating overlapped fingerprints,” IEEE Trans. Inf. Forensics Security, vol. 6, no. 2, Jun. 2011, pp. 346–359.
[52]	Q. Zhao and A. K. Jain, “Model-based separation of overlapping latent fingerprints,” IEEE Trans. Inf. Forensics Security, vol. 7, no. 3, Jun. 2012, pp. 904–918.
[53]	Z Ning ,Z Yali,Y Xin ,J Xiaofei, and T Jie ,” Adaptive Orientation Model Fitting for Latent Overlapped Fingerprints Separation, ” IEEE Trans. Inf. Forensics Security, VOL. 9, NO. 10, OCTOBER 2014 
[54]	J. Feng, Y. Shi, and J. Zhou, “Robust and efficient algorithms for separating latent overlapped fingerprints,” IEEE Trans. Inf. Forensics Security, vol. 7, no. 5, Oct. 2012, pp. 1498–1510.
[55]	M. Akram, S. Nasir, A. Tariq, I. Zafar and W. Khan, “Improved Fingerprint Image Segmentation Using New Modified Gradient Based Technique”, IEEE CCECE/CCGEI, Niagara Falls, Canada, May 5-7, 2008.
[56]	A. Bazen and S. Gerez. “ Directional Field Computation for Fingerprints Based on the Principal Component Analysis of Local Gradients”, ProRISC 2000 Workshop on Circuits, Systems and Signal Processing, Veldhoven, The Netherlands, Nov. 2000.
[57]	N. Otsu, “A threshold selection method from gray-level histogram,” IEEE Trans. Syst. Man Cybern., vol. 9, Jan. 1979 , pp. 62–66.
[58]	R. M. Haralick, S. R. Sternberg, and X. Zhuang, “Image analysis using mathematical morphology,” IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-9, 1987, pp. 523–550.
[59]	H. B. Kekre, V. A. Bharadi, “Fingerprint's Core Point Detection Using Orientation Field” International Conference on Advances in Computing, Control, & Telecommunication Technologies, 2009.
[60]	A. M. Bazen and S. H. Gerez, “Systematic methods for the computation of the directional fields and singular points of fingerprints,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 24, no. 7, Jul.2002, pp. 905–919.
[61]	K. Qian, M. Schott, W. Zheng and J. Dittmann, “Context-based approach of separating contactless captured high-resolution overlapped latent fingerprints,” IET Biom., Vol. 3, Iss 2,2014, pp. 101–112.
[62]	FVC2002: The Second International Fingerprint Verification Competition [Online]. Available: http://bias.csr.unibo.it/fvc2002/
[63]	FVC2000 Web site: http://bias.csr.unibo.it/fvc2000/ 
[64]	FVC2004 Web site: http://bias.csr.unibo.it/fvc2004/ 
[65]	M. Liu, X. Chen, and X. Wang, “Latent Fingerprint Enhancement via   Multi-Scale Patch Based Sparse Representation,” IEEE transactions on information forensics and security, vol. 10, no. 1, January 2015.