CN105678795A - Verification method for field shoeprint image - Google Patents
Verification method for field shoeprint image Download PDFInfo
- Publication number
- CN105678795A CN105678795A CN201610119713.9A CN201610119713A CN105678795A CN 105678795 A CN105678795 A CN 105678795A CN 201610119713 A CN201610119713 A CN 201610119713A CN 105678795 A CN105678795 A CN 105678795A
- Authority
- CN
- China
- Prior art keywords
- point
- personal characteristics
- characteristics point
- footwear
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
Landscapes
- Image Analysis (AREA)
Abstract
The embodiment of the invention provides a verification method for a field shoeprint image. The method comprises: pretreatment is carried out on a field shoeprint image to determine a shoeprint trace; multi-dimension detection is carried out on a first individual feature point of the shoeprint trace by using a corner detection algorithm; a second individual feature point of a connection area of an edge image of the shoeprint trace is detected, wherein the first and second individual feature points include external damage feature, a repairing feature, and an attachment feature of the shoeprint trace; according to the first and second individual feature points, a stable individual feature point of the shoeprint trace is determined; and shoeprint image distinguishment is carried out based on the stable individual feature point. With the method, problems of timeliness and ambiguity of manual verification can be solved. The multi-dimension corner detection strategy for individual features has a characteristic of rotation, zooming, and translation invariance; and accuracy of the verification result is improved.
Description
Technical field
The present embodiments relate to image processing techniques and verification of traces technical field, particularly relate to a kind of field shoe watermark image detection method.
Background technology
In the process of clear up a criminal case, inspection and the analysis of on-the-spot footwear watermark image serve highly important effect for detection work. For the automatic inspection of on-the-spot vestige, both at home and abroad but without forming full ripe solution.
Present stage, in China verification of traces work, through the effort of many experts, defined a set of exclusive technical system, vestige research many in, achieve many scientific and technological achievements advanced in the world, cracked many criminal cases in practice. But verification of traces is but because of the restriction of all factors such as self is theoretical, application, cause its application in investigation practice also exists numerous difficulties. It is mainly manifested in traditional manual manipulation method and seriously constrains verification of traces technology in the effect scouted in solving a case. Undue dependence expert and manually demarcation feature are consuming time and there is ambiguity.
Summary of the invention
The embodiment of the present invention provides a kind of field shoe watermark image method of inspection, to overcome above-mentioned technical problem.
The field shoe watermark image method of inspection of the present invention, including:
Field shoe watermark image is carried out pretreatment and determines footwear impression mark;
Adopt the first personal characteristics point of footwear impression mark described in Corner Detection Algorithm multiple scale detecting;
Detect the second individual character characteristic point of the connected region of the edge image of described footwear impression mark; Described first, second personal characteristics includes: the outer damage feature of described footwear impression mark, repairing feature and attachment feature;
The stable personal characteristics point of described footwear impression mark is determined according to described first personal characteristics point and described second individual character characteristic point;
Footwear watermark image is distinguished according to described personal characteristics point of stablizing.
Further, described field shoe watermark image is carried out pretreatment, including:
Remove the background noise of field shoe watermark image;
Vestige partitioning algorithm is adopted to extract the bianry image of footwear impression mark from described field shoe mark image.
Further, the first personal characteristics point of footwear impression mark described in described employing Corner Detection Algorithm multiple scale detecting, including:
Set the diameter of the first personal characteristics point, determine window according to described diameter;
Determining, according to described window, the first personal characteristics point candidate point that the bianry image of footwear impression mark is corresponding, described first personal characteristics point candidate point is the whole personal characteristics points including footwear impression mark;
Remove the personal characteristics point outside footwear impression mark in described first personal characteristics point candidate point, obtain the first personal characteristics point.
Further, described determine that the bianry image of footwear impression mark includes whole personal characteristics points of footwear impression mark according to described window, including:
Whether the angle point number judged in described window meets setting threshold value, if, it is determined that described angle point is described personal characteristics point, if not, it is determined that described angle point is not personal characteristics point.
Further, the marginal area of described connection described footwear impression mark detects the second individual character characteristic point of described footwear impression mark, including:
Connect described two-value footwear impression mark marginal area and obtain complete area complete area described in labelling;
Calculate the girth of described complete area, if described girth meets setting threshold value, it is determined that described complete area central point is second individual character characteristic point.
Further, the described stable personal characteristics point determining described footwear impression mark according to described first personal characteristics point and described second individual character characteristic point, including:
Merge described first personal characteristics point and described second individual character characteristic point obtains stable personal characteristics point;
Stablize personal characteristics point candidate point according to described screening and obtain stable personal characteristics point.
Further, described stablize between personal characteristics point candidate point that non-similarity screening is described stablizes personal characteristics point candidate point according to described, including:
Delete and described stablize stable personal characteristics point candidate point similar in personal characteristics point candidate point, obtain stable personal characteristics point.
Further, described according to described stablize personal characteristics point distinguish footwear watermark image, including:
Using described personal characteristics point of stablizing as center, the described diameter stablizing personal characteristics point is that the length of side determines square image blocks;
Footwear watermark image is distinguished according to described square image blocks.
The present invention first passes through the feature analyzing characteristic image to be extracted, to Image semantic classification; Then the detection process that human eye is mainly sensitive to the particular geometry of personal characteristics in image is imitated, for the obvious particular geometry of angle point, angle point is detected in multiple dimensioned aspect, for the unconspicuous particular geometry of angle point, meet the particular geometry of size requirements in the detection of edge image aspect; Finally integrate the personal characteristics point extracted, screening conditions are set according to verification of traces priori, the personal characteristics detected is clicked on row screening further, obtains final personal characteristics.
The present invention is directed to on-the-spot mark image, imitate human eye detection process, detection reflection footwear wear the outer sole damage characteristic being different from other footwear in process automatically, repair feature and attachment feature, feature point extraction are divided into two aspects, extract respectively. Automatically the external feature that detection is introduced by the behavioural habits of people etc., has the characteristic that the geometric distortions such as rotation, convergent-divergent, translation is insensitive. Automatic Detection and Extraction feature, it is not necessary to artificial mark picture feature, solves ageing problem and the ambiguity problem of artificial inspection. Multi-scale corner detection strategy for personal characteristics has rotation, convergent-divergent, translation invariance, improves the accuracy of assay.
Accompanying drawing explanation
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, the accompanying drawing used required in embodiment or description of the prior art will be briefly described below, apparently, accompanying drawing in the following describes is some embodiments of the present invention, for those of ordinary skill in the art, under the premise not paying creative work, it is also possible to obtain other accompanying drawing according to these accompanying drawings.
Fig. 1 is the flow chart of the field shoe watermark image method of inspection of the present invention;
Fig. 2 is footwear watermark image the first personal characteristics point schematic diagram of the field shoe watermark image method of inspection of the present invention;
Fig. 3 is the footwear watermark image second individual character characteristic point schematic diagram of the field shoe watermark image method of inspection of the present invention;
The footwear watermark image that Fig. 4 is the field shoe watermark image method of inspection of the present invention stablizes personal characteristics point schematic diagram;
The footwear watermark image that Fig. 5 is the field shoe watermark image method of inspection of the present invention stablizes personal characteristics another schematic diagram of point;
Fig. 6 is the overall flow figure of the field shoe watermark image method of inspection of the present invention.
Detailed description of the invention
For making the purpose of the embodiment of the present invention, technical scheme and advantage clearly, below in conjunction with the accompanying drawing in the embodiment of the present invention, technical scheme in the embodiment of the present invention is clearly and completely described, obviously, described embodiment is a part of embodiment of the present invention, rather than whole embodiments. Based on the embodiment in the present invention, the every other embodiment that those of ordinary skill in the art obtain under not making creative work premise, broadly fall into the scope of protection of the invention.
Fig. 1 is the flow chart of the field shoe watermark image method of inspection of the present invention, as it is shown in figure 1, the method for the present embodiment may include that
Step 101, field shoe watermark image is carried out pretreatment determine footwear impression mark;
First personal characteristics point of footwear impression mark described in step 102, employing Corner Detection Algorithm multiple scale detecting;
Step 103, detect the second individual character characteristic point of the connected region of the edge image of described footwear impression mark; Described first, second personal characteristics includes: the outer damage feature of described footwear impression mark, repairing feature and attachment feature;
Step 104, determine the stable personal characteristics point of described footwear impression mark according to described first personal characteristics point and described second individual character characteristic point;
Step 105, according to described stablize personal characteristics point distinguish footwear watermark image.
Further, described field shoe watermark image is carried out pretreatment, including:
Remove the background noise of field shoe watermark image;
Vestige partitioning algorithm is adopted to extract the bianry image of footwear impression mark from described field shoe watermark image.
Specifically, there is complicated background in usual field shoe watermark image, carries out pretreatment hence for field shoe watermark image, analyze the feature of characteristic image to be extracted, to Image semantic classification, thus removing the background noise of field shoe watermark image, the present embodiment pretreatment adopts image segmentation algorithm to extract footwear impression mark from described field shoe watermark image, and output result is bianry image, and in the present embodiment, image segmentation algorithm is level-set segmentation method. then the pretreated footwear impression mark of Harris Corner Detection Algorithm multiple scale detecting is adopted to obtain the first personal characteristics point, as shown in Figure 2, imitate the detection process that human eye is mainly sensitive to the particular geometry of personal characteristics in image, for the obvious particular geometry of angle point, angle point is detected in multiple dimensioned aspect, secondly the second individual character characteristic point of the connected region of the edge image of footwear impression mark is detected, as shown in Figure 3, the stable personal characteristics point of footwear impression mark is determined finally according to the first personal characteristics point and second individual character characteristic point, as shown in Figure 4, thus distinguishing footwear watermark image according to this stable personal characteristics point. should having non-similarity between personal characteristics, personal characteristics has certain stability, and on some scale effectively, personal characteristics has certain geometrical property to personal characteristics. analyze the feature that the behavioural habits of suspect embody in vestige, analyze the outer damage feature of vestige, repair feature and the embodiment on image of the attachment feature, screening conditions are set, remove pseudo-personal characteristics point.
The present embodiment field shoe watermark image method of inspection, the identification of suspect can be provided important reference by the personal characteristics that this method detects.First pass through the feature analyzing characteristic image to be extracted, to Image semantic classification; Then the detection process that human eye is mainly sensitive to the particular geometry of personal characteristics in image is imitated, for the obvious particular geometry of angle point, angle point is detected in multiple dimensioned aspect, personal characteristics point is obtained after integrating screening angle point, for the unconspicuous particular geometry of angle point, the particular geometry of size requirements is met, with geometry center for personal characteristics point in the detection of edge image aspect; Finally integrate the personal characteristics point extracted, screening conditions are set according to verification of traces priori, the personal characteristics detected is clicked on row screening further, obtains stable personal characteristics. The present embodiment field shoe print mark image personal characteristics automatic detection algorithm, the external feature that detection is introduced by the behavioural habits of people etc. automatically, there is the characteristic that the geometric distortions such as rotation, convergent-divergent, translation is insensitive.
Further, the first personal characteristics point of footwear impression mark described in described employing Harris algorithm multiple scale detecting, including:
Set the diameter of the first personal characteristics point, determine window according to described diameter;
The first personal characteristics point candidate point that the bianry image of footwear impression mark is corresponding is determined according to described window
Remove the personal characteristics point outside footwear impression mark in described first personal characteristics point candidate point, obtain the first personal characteristics point.
Specifically, obtaining personal characteristics point after integrating screening angle point, for the unconspicuous particular geometry of angle point, in edge image aspect, detection meets the particular geometry of size requirements, with geometry center for personal characteristics point; Finally integrate the personal characteristics point extracted. When multiple dimensioned aspect detects personal characteristics, imitate human eye and things is drawn near, by fuzzy change cognitive process clearly, image is carried out Corner Detection respectively under multiple yardsticks. Screening conditions are based on observing mass data and obtain, and are specially within the scope of particular geometry angle point number more than two. Merge multiple dimensioned aspect and personal characteristics point that edge image aspect detects, merge rule for taking the union of the personal characteristics point that two aspects detect. Personal characteristics point for describing same personal characteristics merges.
Further, described determine that the bianry image of footwear impression mark includes whole first personal characteristics point candidate points of footwear impression mark according to described window, including:
Judge that whether the angle point number in described window is more than threshold value T1If, it is determined that described angle point is described personal characteristics point, if not, it is determined that described angle point is not personal characteristics point.
Specifically, for field shoe impression mark image zooming-out the first personal characteristics after pretreated, this first personal characteristics mainly includes the outer damage feature of described footwear impression mark, repairs feature and attachment feature, the present embodiment adopts multiple scale detecting algorithm to detect the first personal characteristics point of described footwear impression mark, and it is as follows that it extracts process:
A, change Gaussian function variances sigma2(standard deviation sigma takes 5 values herein, corresponding 5 yardsticks, value 1,2,3 respectively, 4,5), different gaussian kernel function is produced, with the footwear each layer gaussian kernel function of impression mark image convolution, each layer convolution results is carried out Harris Corner Detection (Corner Detection based on gray level image), obtains footwear impression mark image angle point.
B, with in pretreatment process footwear print bianry image the first personal characteristics is clicked on row filter, if the first personal characteristics point detected does not stamp at footwear, remove this first personal characteristics point;
C, set the diameter d of the first personal characteristics, generally choose the 1/60 of footwear impression mark effective length, window size (square that window is is the length of side with described diameter) is determined according to described diameter, the angle point detected is screened, and concrete screening technique is: judge that whether the angle point number in described window is more than threshold value T1(T herein1Value 2), if, it is determined that described angle point is described first personal characteristics point, if not, it is determined that described angle point is not described first personal characteristics point.
Further, the marginal area of described connection described footwear impression mark detects the second individual character characteristic point of described footwear impression mark, including:
Connect described two-value footwear impression mark marginal area and obtain complete area complete area described in labelling;
Calculate the girth of described complete area, if described girth meets setting threshold value, it is determined that described complete area central point is second individual character characteristic point.
Specifically, the marginal area connecting described footwear impression mark detects the second individual character characteristic point of described footwear impression mark, and it is as follows that it extracts process:
A, two-value footwear impression mark rim detection obtain complete area complete area described in labelling;
B, calculate the girth of described complete area, if described girth meets setting threshold value T2, it is determined that described complete area central point is second individual character characteristic point.
Second individual character characteristic point predominantly detects the unconspicuous personal characteristics of Corner Feature, it is considered to this category feature is approximately circular, and characteristic diameter size is set forth in fisrt feature point detection process, shown in the acquiring method of above-mentioned threshold value such as formula (1)
π d=T2(1)
Wherein, d is the diameter of the first personal characteristics, T2For the perimeter threshold set.
According to the feature that human eye inspection is sensitive to image border, detect personal characteristics point in edge image aspect, edge image is carried out connected region detection, when connected region girth meets setting threshold range, with connected region center for personal characteristics point.
Further, the described stable personal characteristics point determining described footwear impression mark according to described first personal characteristics point and described second individual character characteristic point, including:
Merge described first personal characteristics point and described second individual character characteristic point obtains stable personal characteristics point candidate point;
Stablize the screening of personal characteristics point candidate point described stablize personal characteristics point according to described.
Specifically, merging described first personal characteristics point and described second individual character characteristic point obtains stable personal characteristics point candidate point, it comprises the following steps:
A, described first personal characteristics point and described second individual character characteristic point being merged, merging method, for taking union, obtains stable personal characteristics point candidate point;
When stablizing personal characteristics point candidate point density more than threshold value in window described in B, multiple scale detecting aspect, think that characteristic point describes same personal characteristics in window, then personal characteristics point is merged, personal characteristics points all in window are merged into a bit, the barycenter being in window personal characteristics point;
Further, described stablizing between personal characteristics point candidate point that non-similarity screening is described stablizes personal characteristics point candidate point according to described, it comprises the following steps:
Choose little square frame gray matrix around stable personal characteristics point candidate point and describe this stable personal characteristics point candidate point, ask for each normalizated correlation coefficient stablized between personal characteristics point candidate point gray matrix in region, stablize between personal characteristics point candidate point gray matrix normalizated correlation coefficient value more than setting threshold value T if multiple in region3(implementation process takes T3Equal to 0.5), then remove in region and said similar stable personal characteristics point candidate point.
Should have non-similarity between personal characteristics, if the different personal characteristics detected are similar, then be non-personal characteristics, remove non-personal characteristics.
Further, described according to described stablize personal characteristics point distinguish footwear watermark image, including:
Using described personal characteristics point of stablizing as center, the described diameter stablizing personal characteristics point is that the length of side determines square image blocks;
Footwear watermark image is distinguished according to described square image blocks.
Specifically, the final personal characteristics extracted is centered by personal characteristics point, and personal characteristics diameter d is the square image blocks of the length of side. As shown in Figure 5.
The present invention first passes through the feature analyzing characteristic image to be extracted, to Image semantic classification; Then the detection process that human eye is mainly sensitive to the particular geometry of personal characteristics in image is imitated, for the obvious particular geometry of angle point, angle point is detected in multiple dimensioned aspect, for the unconspicuous particular geometry of angle point, the detection of edge image aspect meets the particular geometry of size requirements; Finally integrate the personal characteristics point extracted, screening conditions are set according to verification of traces priori, the personal characteristics detected is clicked on row screening further, obtains final personal characteristics. The overall flow figure of said method is as shown in Figure 6.
The present invention is directed to field shoe print mark image, imitate human eye detection process, detection reflection footwear wear the outer sole damage characteristic being different from other footwear in process automatically, repair feature and attachment feature, feature point extraction are divided into two aspects, extract respectively. Automatically the external feature that detection is introduced by the behavioural habits of people etc., has the characteristic that the geometric distortions such as rotation, convergent-divergent, translation is insensitive. Automatic Detection and Extraction feature, it is not necessary to artificial mark picture feature, solves ageing problem and the ambiguity problem of artificial inspection. Multi-scale corner detection strategy for personal characteristics has rotation, convergent-divergent, translation invariance, has obvious advantage in context of detection.
In on-the-spot verification of traces process, by analyzing the outer sole damage characteristic of footwear, repairing feature and the reflection in the picture of attachment feature, features described above is reflected as the geometric characteristic being different from shoe sole print feature in the picture, reaches the purpose of detection personal characteristics. Personal characteristics should embody following characteristics on image: should having non-similarity between personal characteristics, personal characteristics has certain stability, and on some scale effectively, personal characteristics has certain geometrical property to personal characteristics. And in desk checking process, human eye is to the particular geometry in image sensitive the geometry of decorative pattern shape (particular geometry refer to be different from image), and the description of particular geometry is broadly divided into the description to shape and yardstick by human eye.
Last it is noted that various embodiments above is only in order to illustrate technical scheme, it is not intended to limit; Although the present invention being described in detail with reference to foregoing embodiments, it will be understood by those within the art that: the technical scheme described in foregoing embodiments still can be modified by it, or wherein some or all of technical characteristic is carried out equivalent replacement; And these amendments or replacement, do not make the essence of appropriate technical solution depart from the scope of various embodiments of the present invention technical scheme.
Claims (8)
1. a field shoe watermark image method of inspection, it is characterised in that including:
Field shoe watermark image is carried out pretreatment and determines footwear impression mark;
Adopt the first personal characteristics point of footwear impression mark described in Corner Detection Algorithm multiple scale detecting;
Detect the second individual character characteristic point of the connected region of the edge image of described footwear impression mark; Described first, second personal characteristics includes: the outer damage feature of described footwear impression mark, repairing feature and attachment feature;
The stable personal characteristics point of described footwear impression mark is determined according to described first personal characteristics point and described second individual character characteristic point;
Footwear watermark image is distinguished according to described personal characteristics point of stablizing.
2. method according to claim 1, it is characterised in that described field shoe watermark image is carried out pretreatment, including:
Remove the background noise of field shoe watermark image;
Vestige partitioning algorithm is adopted to extract the bianry image of footwear impression mark from described field shoe watermark image.
3. method according to claim 2, it is characterised in that the first personal characteristics point of footwear impression mark described in described employing Corner Detection Algorithm multiple scale detecting, including:
Set the diameter of the first personal characteristics point, determine window according to described diameter;
The first personal characteristics point candidate point that the bianry image of footwear impression mark is corresponding is determined according to described window;
Remove the personal characteristics point outside footwear impression mark in described first personal characteristics point candidate point, obtain the first personal characteristics point.
4. method according to claim 3, it is characterised in that described determine the first personal characteristics point candidate point that the bianry image of footwear impression mark is corresponding according to described window, including:
Whether the angle point number judged in described window meets setting threshold value, if, it is determined that described angle point is described personal characteristics point, if not, it is determined that described angle point is not personal characteristics point.
5. method according to claim 1 and 2, it is characterised in that the marginal area of described connection described footwear impression mark detects the second individual character characteristic point of described footwear impression mark, including:
Connect described two-value footwear impression mark marginal area and obtain complete area complete area described in labelling;
Calculate the girth of described complete area, if described girth meets setting threshold value, it is determined that described complete area central point is second individual character characteristic point.
6. method according to claim 1 and 2, it is characterised in that the described stable personal characteristics point determining described footwear impression mark according to described first personal characteristics point and described second individual character characteristic point, including:
Merge described first personal characteristics point and described second individual character characteristic point obtains stable personal characteristics point candidate point;
Stablize between personal characteristics point candidate point that non-similarity screening is described stablizes personal characteristics point candidate point according to described.
7. method according to claim 6, it is characterised in that described stablize between personal characteristics point candidate point that non-similarity screening is described stablizes personal characteristics point candidate point according to described, including:
Delete and described stablize stable personal characteristics point candidate point similar between personal characteristics point candidate point, obtain stable personal characteristics point.
8. method according to claim 1, it is characterised in that described according to described stablize personal characteristics point distinguish footwear watermark image, including:
Using described personal characteristics point of stablizing as center, the described diameter stablizing personal characteristics point is that the length of side determines square image blocks;
Footwear watermark image is distinguished according to described square image blocks.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610119713.9A CN105678795B (en) | 2016-03-02 | 2016-03-02 | A kind of field shoe watermark image method of inspection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610119713.9A CN105678795B (en) | 2016-03-02 | 2016-03-02 | A kind of field shoe watermark image method of inspection |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105678795A true CN105678795A (en) | 2016-06-15 |
| CN105678795B CN105678795B (en) | 2018-09-21 |
Family
ID=56306439
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610119713.9A Active CN105678795B (en) | 2016-03-02 | 2016-03-02 | A kind of field shoe watermark image method of inspection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105678795B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110287843A (en) * | 2019-06-18 | 2019-09-27 | 清华大学深圳研究生院 | A kind of historical relic finger-print region method for selecting |
| CN111000327A (en) * | 2019-10-24 | 2020-04-14 | 晋江市达亿经编织造有限公司 | Breathable mesh vamp capable of automatically eliminating shoe marks |
| CN111860500A (en) * | 2020-07-10 | 2020-10-30 | 大连海事大学 | Shoe print wear area detection and edge tracing method |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102867311A (en) * | 2011-07-07 | 2013-01-09 | 株式会社理光 | Target tracking method and target tracking device |
| CN104915932A (en) * | 2015-05-19 | 2015-09-16 | 中国电子科技集团公司第五十研究所 | Target feature-based holographic radar image preprocessing and target extraction method |
-
2016
- 2016-03-02 CN CN201610119713.9A patent/CN105678795B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102867311A (en) * | 2011-07-07 | 2013-01-09 | 株式会社理光 | Target tracking method and target tracking device |
| CN104915932A (en) * | 2015-05-19 | 2015-09-16 | 中国电子科技集团公司第五十研究所 | Target feature-based holographic radar image preprocessing and target extraction method |
Non-Patent Citations (4)
| Title |
|---|
| H. SU 等: "Local image Features for Shoeprint Image Retrieval", 《PROCEEDINGS OF THE BRITISH MACHINE VISION CONFERENCE 2007》 * |
| RONNY: "斑点检测", 《HTTP://WWW.CNBLOGS.COM/RONNY/P/3895883.HTML》 * |
| S. ALMAADEED 等: "Partial shoeprint retrieval using multiple point-of-interest detectors and SIFT descriptors", 《INTEGRATED COMPUTER-AIDED ENGINEERING》 * |
| 葛盼盼 等: "基于 Harris角点和SURF特征的遥感图像匹配算法", 《计算机应用研究》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110287843A (en) * | 2019-06-18 | 2019-09-27 | 清华大学深圳研究生院 | A kind of historical relic finger-print region method for selecting |
| CN110287843B (en) * | 2019-06-18 | 2022-01-25 | 清华大学深圳研究生院 | Cultural relic fingerprint area selection method |
| CN111000327A (en) * | 2019-10-24 | 2020-04-14 | 晋江市达亿经编织造有限公司 | Breathable mesh vamp capable of automatically eliminating shoe marks |
| CN111860500A (en) * | 2020-07-10 | 2020-10-30 | 大连海事大学 | Shoe print wear area detection and edge tracing method |
| CN111860500B (en) * | 2020-07-10 | 2024-03-19 | 大连海事大学 | Shoe stamp wearing area detection and edge tracing method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105678795B (en) | 2018-09-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105894036B (en) | A kind of characteristics of image template matching method applied to mobile phone screen defects detection | |
| Reid et al. | A semi-automated methodology for discontinuity trace detection in digital images of rock mass exposures | |
| CN102937595B (en) | Method, device and system for detecting printed circuit board (PCB) | |
| JP7347836B2 (en) | Real-time automatic detection method for 2D PCB appearance defects based on deep learning | |
| CN105205488B (en) | Word area detection method based on Harris angle points and stroke width | |
| WO2017181724A1 (en) | Inspection method and system for missing electronic component | |
| CN105139386A (en) | Image processing method for quickly and automatically detecting soldered dot unsatisfied products of electric connectors | |
| CN107016394B (en) | Cross fiber feature point matching method | |
| CN105718552A (en) | Clothing freehand sketch based clothing image retrieval method | |
| CN104680550A (en) | Method for detecting defect on surface of bearing by image feature points | |
| CN104182973A (en) | Image copying and pasting detection method based on circular description operator CSIFT (Colored scale invariant feature transform) | |
| CN109741314A (en) | A kind of visible detection method and system of part | |
| CN107516085B (en) | Method for automatically removing black edges based on document image | |
| CN111160451A (en) | Flexible material detection method and storage medium thereof | |
| CN105678795A (en) | Verification method for field shoeprint image | |
| CN112288760B (en) | Adherent cell image screening method and system and cell image analysis method | |
| CN110838117A (en) | Rock face porosity identification method based on hole wall image | |
| Xie et al. | Crater detection using the morphological characteristics of Chang'E-1 digital elevation models | |
| CN104866850B (en) | A kind of optimization method of text image binaryzation | |
| Li et al. | A method of surface defect detection of irregular industrial products based on machine vision | |
| CN109409211A (en) | The processing method and system of Chinese character skeleton pen section | |
| CN102722701B (en) | Visual monitoring method and device in fingerprint collection process | |
| CN108717544A (en) | A kind of newspaper sample manuscript word automatic testing method based on intelligent image analysis | |
| CN108154116A (en) | A kind of image-recognizing method and system | |
| CN105160300B (en) | A kind of text abstracting method based on level-set segmentation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |