Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Interest Curves: Concept, Evaluation, Implementation and Applications
Umeå University, Faculty of Science and Technology, Department of Applied Physics and Electronics. (DML,I2lab)
2015 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

Image features play important roles in a wide range of computer vision applications, such as image registration, 3D reconstruction, object detection and video understanding. These image features include edges, contours, corners, regions, lines, curves, interest points, etc. However, the research is fragmented in these areas, especially when it comes to line and curve detection. In this thesis, we aim to discover, integrate, evaluate and summarize past research as well as our contributions in the area of image features. This thesis provides a comprehensive framework of concept, evaluation, implementation, and applications for image features.

Firstly, this thesis proposes a novel concept of interest curves. Interest curves is a concept derived and extended from interest points. Interest curves are significant lines and arcs in an image that are repeatable under various image transformations. Interest curves bring clear guidelines and structures for future curve and line detection algorithms and related applications.

Secondly, this thesis presents an evaluation framework for detecting and describing interest curves. The evaluation framework provides a new paradigm for comparing the performance of state-of-the-art line and curve detectors under image perturbations and transformations.

Thirdly, this thesis proposes an interest curve detector (Distinctive Curves, DICU), which unifies the detection of edges, corners, lines and curves. DICU represents our state-of-the-art contribution in the areas concerning the detection of edges, corners, curves and lines. Our research efforts cover the most important attributes required by these features with respect to robustness and efficiency.

Interest curves preserve richer geometric information than interest points. This advantage gives new ways of solving computer vision problems. We propose a simple description method for curve matching applications. We have found that our proposed interest curve descriptor outperforms all state-of-the-art interest point descriptors (SIFT, SURF, BRISK, ORB, FREAK). Furthermore, in our research we design a novel object detection algorithm that only utilizes DICU geometries without using local feature appearance. We organize image objects as curve chains and to detect an object, we search this curve chain in the target image using dynamic programming. The curve chain matching is scale and rotation-invariant as well as robust to image deformations. These properties have given us the possibility of resolving the rotation-variance problem in object detection applications. In our face detection experiments, the curve chain matching method proves to be scale and rotation-invariant and very computational efficient.

Abstract [sv]

Bilddetaljer har en viktig roll i ett stort antal applikationer för datorseende, t.ex., bildregistrering, 3D-rekonstruktion, objektdetektering och videoförståelse. Dessa bilddetaljer inkluderar kanter, konturer, hörn, regioner, linjer, kurvor, intressepunkter, etc. Forskningen inom dessa områden är splittrad, särskilt för detektering av linjer och kurvor. I denna avhandling, strävar vi efter att hitta, integrera, utvärdera och sammanfatta tidigare forskning tillsammans med vår egen forskning inom området för bildegenskaper. Denna avhandling presenterar ett ramverk för begrepp, utvärdering, utförande och applikationer för bilddetaljer.

För det första föreslår denna avhandling ett nytt koncept för intressekurvor. Intressekurvor är ett begrepp som härrör från intressepunkter och det är viktiga linjer och bågar i bilden som är repeterbara oberoende av olika bildtransformationer. Intressekurvor ger en tydlig vägledning och struktur för framtida algoritmer och relaterade tillämpningar för kurv- och linjedetektering.

För det andra, presenterar denna avhandling en utvärderingsram för detektorer och beskrivningar av intressekurvor. Utvärderingsramverket utgör en ny paradigm för att jämföra resultatet för de bästa möjliga teknikerna för linje- och kurvdetektorer vid bildstörningar och bildtransformationer.

För det tredje presenterar denna avhandling en detektor för intressekurvor (Distinctive curves, DICU), som förenar detektering av kanter, hörn, linjer och kurvor. DICU representerar vårt främsta bidrag inom området detektering av kanter, hörn, kurvor och linjer. Våra forskningsinsatser täcker de viktigaste attribut som krävs av dessa funktioner med avseende på robusthet och effektivitet.

Intressekurvor innehåller en rikare geometrisk information än intressepunkter. Denna fördel öppnar för nya sätt att lösa problem för datorseende. Vi föreslår en enkel beskrivningsmetod för kurvmatchningsapplikationer och den föreslagna deskriptorn för intressekurvor överträffar de bästa tillgängliga deskriptorerna för intressepunkter (SIFT, SURF, BRISK, ORB, och FREAK). Dessutom utformar vi en ny objektdetekteringsalgoritm som bara använder geometri för DICU utan att använda det lokala utseendet. Vi organiserar bildobjekt som kurvkedjor och för att upptäcka ett objekt behöver vi endast söka efter denna kurvkedja i målbilden med hjälp av dynamisk programmering. Kurvkedjematchningen är oberoende av skala och rotationer samt robust vid bilddeformationer. Dessa egenskaper ger möjlighet att lösa problemet med rotationsberoende inom objektdetektering. Vårt ansiktsigenkänningsexperiment visar att kurvkedjematchning är oberoende av skala och rotationer och att den är mycket beräkningseffektiv.

Place, publisher, year, edition, pages
Umeå: Umeå Universitet , 2015. , 206 p.
Series
Digital Media Lab, ISSN 1652-6295 ; 21
Keyword [en]
scale-invariance, edge, corner, curve, line, matching, object detection
National Category
Electrical Engineering, Electronic Engineering, Information Engineering
Research subject
Signal Processing
Identifiers
URN: urn:nbn:se:umu:diva-111175ISBN: 978-91-7601-353-3 (print)OAI: oai:DiVA.org:umu-111175DiVA: diva2:867814
Public defence
2015-11-27, MIT-huset, MA121, Umeå universitet, Umeå, 13:00 (English)
Opponent
Supervisors
Projects
INTRO – INteractive RObotics research network
Funder
EU, FP7, Seventh Framework Programme
Available from: 2015-11-06 Created: 2015-11-06 Last updated: 2015-11-10Bibliographically approved
List of papers
1. Independent Thresholds on Multi-scale Gradient Images
Open this publication in new window or tab >>Independent Thresholds on Multi-scale Gradient Images
2013 (English)In: The 1st IEEE/IIAE International Conference on Intelligent Systems and Image Processing 2013 (ICISIP2013), Kitakyushu, Japan, 2013, 124-131 p.Conference paper, Published paper (Refereed)
Abstract [en]

In this paper we propose a multi-scale edge detection algorithm based on proportional scale summing. Our analysis shows that proportional scale summing successfully improves edge detection rate by applying independent thresholds on multi-scale gradient images. The proposed method improves edge detection and localization by summing gradient images with a proportional parameter cn (c < 1); which ensures that the detected edges are as close as possible to the fine scale. We employ non-maxima suppression and thinning step similar to Canny edge detection framework on the summed gradient images. The proposed method can detect edges successfully and experimental results show that it leads to better edge detection performance than Canny edge detector and scale multiplication edge detector.

Place, publisher, year, edition, pages
Kitakyushu, Japan: , 2013
Series
The Institute of Industrial Applications Engineers, Japan
Keyword
Edge, Detection, Multi-scale
National Category
Signal Processing Computer Vision and Robotics (Autonomous Systems)
Research subject
Computerized Image Analysis
Identifiers
urn:nbn:se:umu:diva-82278 (URN)10.12792/icisip2013.027 (DOI)
Conference
The 1st IEEE/IIAE International Conference on Intelligent Systems and Image Processing 2013 (ICISIP2013)
Projects
INTRO – INteractive RObotics research network
Funder
EU, FP7, Seventh Framework Programme
Available from: 2013-10-29 Created: 2013-10-29 Last updated: 2016-02-23Bibliographically approved
2. Fast edge detection by center of mass
Open this publication in new window or tab >>Fast edge detection by center of mass
Show others...
2013 (English)In: The 1st IEEE/IIAE International Conference on Intelligent Systems and Image Processing 2013 (ICISIP2013), Kitakyushu, Japan, 2013, 103-110 p.Conference paper, Published paper (Refereed)
Abstract [en]

In this paper, a novel edge detection method that computes image gradient using the concept of Center of Mass (COM) is presented. The algorithm runs with a constant number of operations per pixel independently from its scale by using integral image. Compared with the conventional convolutional edge detector such as Sobel edge detector, the proposed method performs faster when region size is larger than 9×9. The proposed method can be used as framework for multi-scale edge detectors when the goal is to achieve fast performance. Experimental results show that edge detection by COM is competent with Canny edge detection.

Place, publisher, year, edition, pages
Kitakyushu, Japan: , 2013
Series
The Institute of Industrial Applications Engineers, Japan
Keyword
Edge detection, Center of mass, Integral image, Multi-scale, Fast computing.
National Category
Signal Processing Computer Vision and Robotics (Autonomous Systems)
Research subject
Computerized Image Analysis
Identifiers
urn:nbn:se:umu:diva-82350 (URN)10.12792/icisip2013.024 (DOI)
Conference
The 1st IEEE/IIAE International Conference on Intelligent Systems and Image Processing 2013 (ICISIP2013)
Projects
INTRO – INteractive RObotics research network
Funder
EU, FP7, Seventh Framework Programme
Available from: 2013-10-30 Created: 2013-10-30 Last updated: 2016-02-23Bibliographically approved
3. Restricted Hysteresis Reduce Redundancy in Edge Detection
Open this publication in new window or tab >>Restricted Hysteresis Reduce Redundancy in Edge Detection
2013 (English)In: Journal of Signal and Information Processing, ISSN 2159-4465, E-ISSN 2159-4481, Vol. 4, no 3B, 158-163 p.Article in journal, Editorial material (Refereed) Published
Abstract [en]

In edge detection algorithms, there is a common redundancy problem, especially when the gradient direction is close to -135°, -45°, 45°, and 135°. Double edge effect appears on the edges around these directions. This is caused by the discrete calculation of non-maximum suppression. Many algorithms use edge points as feature for further task such as line extraction, curve detection, matching and recognition. Redundancy is a very important factor of algorithm speed and accuracy. We find that most edge detection algorithms have redundancy of 50% in the worst case and 0% in the best case depending on the edge direction distribution. The common redundancy rate on natural images is approximately between 15% and 20%. Based on Canny’s framework, we propose a restriction in the hysteresis step. Our experiment shows that proposed restricted hysteresis reduce the redundancy successfully.

Keyword
edge detection, hysteresis, non-maximum suppression, redundancy
National Category
Computer Vision and Robotics (Autonomous Systems) Signal Processing
Research subject
Computerized Image Analysis
Identifiers
urn:nbn:se:umu:diva-82354 (URN)10.4236/jsip.2013.43B028 (DOI)
Projects
INTRO – INteractive RObotics research network
Funder
EU, FP7, Seventh Framework Programme
Available from: 2013-10-30 Created: 2013-10-30 Last updated: 2017-12-06Bibliographically approved
4. Scale-invariant corner keypoints
Open this publication in new window or tab >>Scale-invariant corner keypoints
(English)Manuscript (preprint) (Other academic)
Abstract [en]

Effective and efficient generation of keypoints from images is the first step of many computer vision applications, such as object matching. The last decade presented us with an arms race toward faster and more robust keypoint detection, feature description and matching. This resulted in several new algorithms, for example Scale Invariant Features Transform (SIFT), Speed-up Robust Feature (SURF), Oriented FAST and Rotated BRIEF (ORB) and Binary Robust Invariant Scalable Keypoints (BRISK). The keypoint detection has been improved using various techniques in most of these algorithms. However, in the search for faster computing, the accuracy of the algorithms is decreasing. In this paper, we present SICK (Scale-Invariant Corner Keypoints), which is a novel method for fast keypoint detection. Our experiment results show that SICK is faster to compute and more robust than recent state-of-the-art methods. 

Keyword
Keypoint detection, image matching, edge detection, corner detection, scale-space
National Category
Electrical Engineering, Electronic Engineering, Information Engineering
Research subject
Signal Processing
Identifiers
urn:nbn:se:umu:diva-111182 (URN)
Conference
IEEE International Conference on Image Processing, October 2014
Note

IEEE International Conference on Image Processing, October 2014

Available from: 2015-11-06 Created: 2015-11-06 Last updated: 2016-02-23
5. Fast edge filter and multi-scale edge detection
Open this publication in new window or tab >>Fast edge filter and multi-scale edge detection
(English)Manuscript (preprint) (Other academic)
Abstract [en]

The first step of efficient edge detection is to use a filter to detect intensity change. The filter size is a parameter which affects the edge detection result. A filter of large size is less sensitive to noise while a filter of small size is more accurate when locating edges. This gives the user a choice of choosing the proper filter size depending on the situation. A more stable edge detection approach is multi-scale edge detection, which detects gradients using several filter sizes.  The time consumption of a conventional edge filter is usually  or , where w is the width of the filter. Therefore, using filters of large size or multi-scale filters is not very efficient. We propose an efficient edge detection method with  time consumption. It uses the center of mass concept and utilizes the power of integral images to achieve this efficiency. The results of our experiments show that the proposed edge detector is very stable and we also propose a simplified multi-scale edge detection scheme which can be used in practical operations.  

Keyword
edge detection, fast, scale-space
National Category
Electrical Engineering, Electronic Engineering, Information Engineering
Research subject
Signal Processing
Identifiers
urn:nbn:se:umu:diva-111183 (URN)
Available from: 2015-11-06 Created: 2015-11-06 Last updated: 2016-02-23
6. Distinctive curve features
Open this publication in new window or tab >>Distinctive curve features
2016 (English)In: Electronics Letters, ISSN 0013-5194, E-ISSN 1350-911X, Vol. 52, no 3, 197-198 p.Article in journal (Other academic) Published
Abstract [en]

Curves and lines are geometrical, abstract features of an image. Whereas interest points are more limited, curves and lines provide much more information of the image structure. However, the research done in curve and line detection is very fragmented. The concept of scale space is not yet fused very well into curve and line detection. Keypoint (e.g. SIFT, SURF, ORB) is a successful concept which represent features (e.g. blob, corner etc.) in scale space. Stimulated by the keypoint concept, a method which extracts distinctive curves (DICU) in scale space, including lines as a special form of curve features is proposed. A curve feature can be represented by three keypoints (two end points, and one middle point). A good way to test the quality of detected curves is to analyse the repeatability under various image transformations. DICU using the standard Oxford benchmark is evaluated. The overlap error is calculated by averaging the overlap error of three keypoints on the curve. Experiment results show that DICU achieves good repeatability comparing with other state-of-the-art methods. To match curve features, a relatively uncomplicated way is to combine local descriptors of three keypoints on each curve.

Keyword
curve detection, line detection, feature matching
National Category
Electrical Engineering, Electronic Engineering, Information Engineering
Research subject
Signal Processing
Identifiers
urn:nbn:se:umu:diva-111184 (URN)10.1049/el.2015.3495 (DOI)000369674000014 ()
Available from: 2015-11-06 Created: 2015-11-06 Last updated: 2017-12-01Bibliographically approved
7. Distinctive curves: unified scale-invariant detection of edges, corners, lines and curves
Open this publication in new window or tab >>Distinctive curves: unified scale-invariant detection of edges, corners, lines and curves
(English)Manuscript (preprint) (Other academic)
Abstract [en]

This paper aims to broaden the scope of shape related features including edges, corners, lines and curves: 1) Edges, corners, lines, curves are all shape related features. In the past, the detection of each type of feature is usually solved independently under certain hypotheses. Our proposed distinctive curve detection method (DICU) solves the detection of all these type of features together. 2) Compared to the development in scale-invariant interest point detectors which have adopted more objective robustness measures using repeatability score, the research in line and curve features is still limited to “true/false positive” measures. DICU detection utilizes the scale-space concept and proves that curve features can be as robust as scale-invariant interest points. DICU has three advantages: 1) DICU outputs multi-type features which can benefit future computer vision applications. At the same time, the computational efficiency is unaffected, after detecting edges, only 5% additional computation is needed to detect corners, lines, and curves. 2) It is robust under various image perturbations and transformations and outperforms state-of-the-art interest point detectors and line detectors. At the same time, all types of detected features are robust. 3) Curve features contains more geometric information than points. Our curve matching test shows that curve matching can outperform interest point matching. 

Keyword
curve, line, corner, feature matching, scale-invariance
National Category
Electrical Engineering, Electronic Engineering, Information Engineering
Research subject
Signal Processing
Identifiers
urn:nbn:se:umu:diva-111186 (URN)
Available from: 2015-11-06 Created: 2015-11-06 Last updated: 2017-03-27Bibliographically approved
8. Scale & rotation-invariant matching with curve chain
Open this publication in new window or tab >>Scale & rotation-invariant matching with curve chain
(English)Manuscript (preprint) (Other academic)
Abstract [en]

This paper presents a new methodology that matches image geometry using a curve chain. A curve chain is defined as a 1-dimensional arrangement of curves. The idea is to match images without using local descriptors and apply this concept into applications. This paper have two contributions. First, we present a novel curve feature which is scale & rotation – invariant. Secondly, we present an efficient scale & rotational-invariant matching method which matches curve chains in the scene. The efficacy is benefited by three factors. Firstly, matching a 1-dimensional curve chain can achieve quadratic operations when dynamic programming is used.  Secondly, curves are salient features that naturally reduce the dimensionality compared with scanning all possible locations. Thirdly, curves provide stable relational cues between neighbouring curves. Such stable relational cues reduce the computation to linear operations by avoiding searching all combinations of curves in dynamic programming. The advantages of the method has good potential to benefit application including point correspondence matching, object detection, etc.  In point correspondence experiments our method yields a good total matching score on various image transformations. At the same time, the proposed method shows good potential of matching non-rigid object such as faces with scale & rotation invariance.

Keyword
curve feature, matching, object detection
National Category
Electrical Engineering, Electronic Engineering, Information Engineering
Research subject
Signal Processing
Identifiers
urn:nbn:se:umu:diva-111189 (URN)
Available from: 2015-11-06 Created: 2015-11-06 Last updated: 2017-03-27Bibliographically approved

Open Access in DiVA

Interest Curves: Concept, Evaluation, Implementation, and Applications(2807 kB)730 downloads
File information
File name FULLTEXT02.pdfFile size 2807 kBChecksum SHA-512
b823a8aaa8408be882873adfb8d1979fc1d93927b6fc9f165e2b0e459c8d11d26f4635555fb64fc6c512de90518012547846f28e9c71fdbc80df849a79684987
Type fulltextMimetype application/pdf
Spikblad(183 kB)12 downloads
File information
File name SPIKBLAD01.pdfFile size 183 kBChecksum SHA-512
78998d2d2af93dfa48abb7ab05b5279f20a1279bf5343dda18e80a71d4d272cd9d18c8577f94be6bd9a0e483e163574e50abac56ae1b5a2b840e0f86957c5bb5
Type spikbladMimetype application/pdf

Search in DiVA

By author/editor
Li, Bo
By organisation
Department of Applied Physics and Electronics
Electrical Engineering, Electronic Engineering, Information Engineering

Search outside of DiVA

GoogleGoogle Scholar
Total: 730 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

isbn
urn-nbn

Altmetric score

isbn
urn-nbn
Total: 5589 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf