CN105468921B - Alimentary canal capsule endoscope video scans drawing generating method - Google Patents
Alimentary canal capsule endoscope video scans drawing generating method Download PDFInfo
- Publication number
- CN105468921B CN105468921B CN201510894392.5A CN201510894392A CN105468921B CN 105468921 B CN105468921 B CN 105468921B CN 201510894392 A CN201510894392 A CN 201510894392A CN 105468921 B CN105468921 B CN 105468921B
- Authority
- CN
- China
- Prior art keywords
- colourity
- rotation
- rectangle
- anglec
- image block
- 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.)
- Expired - Fee Related
Links
- 239000002775 capsule Substances 0.000 title claims abstract description 29
- 238000000034 method Methods 0.000 title claims abstract description 25
- 238000003745 diagnosis Methods 0.000 abstract description 10
- 201000010099 disease Diseases 0.000 abstract description 6
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 abstract description 6
- 238000010586 diagram Methods 0.000 description 6
- 210000004347 intestinal mucosa Anatomy 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 3
- 238000007689 inspection Methods 0.000 description 3
- 239000002893 slag Substances 0.000 description 3
- 230000002496 gastric effect Effects 0.000 description 2
- 210000004877 mucosa Anatomy 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000029087 digestion Effects 0.000 description 1
- 210000001035 gastrointestinal tract Anatomy 0.000 description 1
- 239000003292 glue Substances 0.000 description 1
- 210000000936 intestine Anatomy 0.000 description 1
- 239000000463 material Substances 0.000 description 1
Classifications
-
- G06F19/321—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/60—Rotation of whole images or parts thereof
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Endoscopes (AREA)
Abstract
Drawing generating method is scanned the invention provides a kind of alimentary canal capsule endoscope video.After this scans drawing generating method by the way that image is carried out into multiple rotary, determine optimal the colourity anglec of rotation and the optimal brightness anglec of rotation of image respectively in colourity and luminance component, then most suitable angle is selected to rotate image from the optimal colourity anglec of rotation and the optimal brightness anglec of rotation, finally vertically cut pixel column per two field picture from according to the angle is postrotational along picture centre line and merge generation overview, through the above way, the present invention can accurately show gastral integral status, the indication range of alimentary canal viewing area can be improved, improve diagnosis efficiency of the doctor to alimentary canal capsule endoscope video, reduce failing to pinpoint a disease in diagnosis for alimentary canal viewing area.
Description
Technical field
The present invention relates to technical field of image processing, more particularly to a kind of overview of alimentary canal capsule endoscope video
Generation method.
Background technology
Capsule endoscope inspection is a line technology of current disease of digestive tract checkout and diagnosis.Capsule endoscope is a kind of capsule
The micro-camera device for being used to shoot human body alimentary canal of shape.Patient is from the capsule endoscope is swallowed to excreting, capsule
Endoscope works about 8 hours in human body and shoots about 50000 two field pictures.The major defect of capsule endoscope inspection is：Often
Part video bag contains substantial amounts of image, and every image will carry out hand inspection by doctor, not only expends time length, and it is strong to work
Degree is big, and easily causes and fail to pinpoint a disease in diagnosis after doctor's fatigue.Therefore, capsule endoscope video is handled to aid in using computer
Diagnosis has the extensive market demand.
The computer analytical technology of existing capsule endoscope video mainly vertically cuts one from every two field picture center
Individual pixel column is spliced overview, is that can allow doctor from the rapid gastral monolithic for holding patient the advantages of overview
Condition, but it is also obvious that precisely due to the direction that cuts of pixel column is fixed, if containing food in video image the shortcomings that overview
Thing mixes the not visible region such as slag, and pixel column is cut to be mixed on slag in food, cannot accurately show gastral integral status, easily
Cause to fail to pinpoint a disease in diagnosis.
The content of the invention
The purpose of the present invention is achieved through the following technical solutions：The present invention solves the technical problem of offer
A kind of alimentary canal capsule endoscope video scans drawing generating method, can accurately show gastral integral status.
In order to solve the above technical problems, one aspect of the present invention is：There is provided and peeped in a kind of alimentary canal capsule
Mirror video scans drawing generating method, including：S1：After each two field picture of video is transformed into hsv color space, by each frame
Image carries out the rotation of multiple unit angle around image center, wherein, the repeatedly unit angle sum is 180 degree；S2：It is right
Each two field picture and its each postrotational image vertically cut rectangle chromatic diagram picture on colourity H components along picture centre line
Block, and mean filter is carried out to rectangle colourity image block and obtains chroma pixel row, and to each two field picture and its each rotation
Image afterwards vertically cuts rectangle luminance picture block on brightness V component along picture centre line, and rectangle luminance picture block is entered
Row mean filter obtains luminance pixel row；S3：Variance yields, average and the kurtosis arranged according to each chroma pixel of each two field picture
Value calculates colourity saliency value, and using the anglec of rotation corresponding to minimal color saliency value as the optimal colourity anglec of rotation, Yi Jigen
The variance yields that is arranged according to each luminance pixel of each two field picture, average and kurtosis value calculate brightness saliency value, and by minimum brightness
The anglec of rotation corresponding to saliency value is as the optimal brightness anglec of rotation；S4：By each two field picture according to the optimal colourity anglec of rotation
Rotated, vertically cut the first rectangular image block along picture centre line after rotation, and calculate the first square on the chroma components
First difference value of shape image block, and each two field picture is rotated according to the optimal brightness anglec of rotation, after rotation edge
Picture centre line vertically cuts the second rectangular image block, and calculates the second difference of the second rectangular image block on the chroma components
Value；S5：The first difference value and the second difference value of each two field picture are compared, and it is poor more than second to count the first difference value
First frame number of the image of different value and the second difference value are more than the second frame number of the image of the first difference value；S6：If the first frame
Number is more than the second frame number, and each two field picture is rotated according to the optimal colourity anglec of rotation, if the second frame number is more than first
Frame number, each two field picture is rotated according to the optimal brightness anglec of rotation；S7：Along picture centre after the rotation of each two field picture
Line vertically cuts pixel column, and the pixel column of each two field picture is merged into generation overview.
Preferably, the unit angle is 5-15 degree.
Preferably, the height of rectangle colourity image block and rectangle the luminance picture block be image height, the rectangle
The width of colourity image block and rectangle luminance picture block is 9 or 11 pixel wides.
Preferably, when carrying out mean filter, size and rectangle colourity image block or the rectangle luminance picture of filter window
The width of block is identical.
Preferably, described the step of obtaining chroma pixel row to rectangle colourity image block progress mean filter, is specially：It is right
Every one-row pixels of rectangle colourity image block carry out taking mean operation to obtain chroma pixel row；It is described that rectangle luminance picture block is entered
Row mean filter obtains the step of chroma pixel row and is specially：Every one-row pixels of rectangle luminance picture block are carried out taking average to transport
Calculation obtains luminance pixel row.
Preferably, the calculating formula of the colourity saliency value and brightness saliency value is：
Wherein, c is that chroma pixel arranges or luminance pixel arranges, and σ (c) is arranged for chroma pixel or the variance yields of luminance pixel row, μ
(c) it is the average of chroma pixel row or luminance pixel row, κ (c) is arranged for chroma pixel or the kurtosis value of luminance pixel row, sinh
() is hyperbolic sine function.
Preferably, it is described calculate the first rectangular image block on the chroma components the first difference value the step of be specially：Meter
The first Euclidean distance of the chroma histogram of the first rectangular image block top half and the latter half is calculated, by the first Euclidean distance amount
Turn to the first difference value；It is described calculate the second rectangular image block on the chroma components the second difference value the step of be specially：Meter
The second Euclidean distance of the chroma histogram of the second rectangular image block top half and the latter half is calculated, by the second Euclidean distance amount
Turn to the second difference value.
Preferably, before step S1, in addition to：Video is segmented sequentially in time.
The situation of prior art is different from, the beneficial effects of the invention are as follows：The alimentary canals such as enteric cavity, gastrointestinal mucosa can be improved
The indication range of viewing area, diagnosis efficiency of the doctor to alimentary canal capsule endoscope video is improved, reduce alimentary canal visible area
Fail to pinpoint a disease in diagnosis in domain.
Brief description of the drawings
Fig. 1 is the schematic flow sheet for scanning drawing generating method of alimentary canal capsule endoscope video of the embodiment of the present invention.
Fig. 2 is to obtain the signal of chroma pixel row or luminance pixel row using the drawing generating method of scanning of the embodiment of the present invention
Figure.
Fig. 3 is that the drawing generating method of scanning for applying the embodiment of the present invention cuts pixel column and cuts pixel using prior art
The contrast schematic diagram of row.
Fig. 4 is to scan drawing generating method and application prior art to the intestines containing swill using the embodiment of the present invention
The contrast schematic diagram of the image pattern generation overview in road.
Fig. 5 is to scan the image sample of drawing generating method and application prior art to normal bowel using the embodiment of the present invention
The contrast schematic diagram of this generation overview.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation describes, it is clear that described embodiment is only the part of the embodiment of the present invention, rather than whole embodiments.It is based on
Embodiment in the present invention, those of ordinary skill in the art are obtained every other under the premise of creative work is not made
Embodiment, belong to the scope of protection of the invention.
It is that the flow for scanning drawing generating method of alimentary canal capsule endoscope video of the embodiment of the present invention is illustrated referring to Fig. 1
Figure.The drawing generating method of scanning of the present embodiment comprises the following steps：
S1：After each two field picture of video is transformed into hsv color space, each two field picture is carried out around image center
The rotation of multiple unit angle, wherein, multiple unit angle sum is 180 degree.
Wherein, the image of capsule endoscope video is rgb space image, after hsv color space is transformed to, is peeped in capsule
The image of mirror video is changed into HSV space image.Hsv color space has three components, is colourity H, saturation degree S, brightness V respectively
Component.
Image center is the geometric center of image, and image is after multiple rotary, because multiple unit angle sum is
180 degree, image just have rotated 180 degree from 0 degree.Alternatively, unit angle is 5-15 degree.So that unit angle is 10 degree as an example, figure
As 10 degree of rotation every time, then need rotation 17 times.
In the present embodiment, before step S1, in addition to：Video is segmented sequentially in time.In view of glue
Capsule endoscopic video contains the image of magnanimity, and the so more images of single treatment may require higher for computer, and this implementation
Example is used as the data of single treatment using every section of video by will be segmented video sequentially in time.
S2：Square is vertically cut along picture centre line on the chroma components to each two field picture and its each postrotational image
Shape and color degree image block, and mean filter is carried out to rectangle colourity image block and obtains chroma pixel row, and to each two field picture and
Postrotational image vertically cuts rectangle luminance picture block on luminance component along picture centre line every time for it, and to rectangle brightness
Image block carries out mean filter and obtains luminance pixel row.
Wherein, chroma pixel row and luminance pixel row can be in step s 2 and meanwhile obtain or in step
Successively obtained in S2.For each two field picture and its each postrotational image, by respectively being isolated by colourity H and brightness V
Two components, cutting rectangle colourity image block on the chroma components respectively and rectangle luminance picture is cut on luminance component
Block.As shown in Fig. 2 (a), the graphical representation enteron aisle in Fig. 2 (a), the image is vertically cut after rotation along picture centre line
Rectangle colourity image block or rectangle luminance picture block (see in figure shown in white line rectangle frame).
Because the least unit of image is pixel, therefore each row and column of rectangle colourity image block and rectangle luminance picture block
Formed by pixel, alternatively, the height of rectangle colourity image block and rectangle luminance picture block is the height of image, rectangle colourity
The width of image block and rectangle luminance picture block can be 9 or 11 pixel wides.
By carrying out on pixel level, mean filter can obtain chroma pixel row and luminance pixel arranges.In the present embodiment
In, carrying out the step of mean filter obtains chroma pixel row to rectangle colourity image block is specially：To rectangle colourity image block
Carry out taking mean operation to obtain chroma pixel row per one-row pixels.Mean filter is carried out to rectangle luminance picture block and obtains colourity picture
Element row the step of be specially：Every one-row pixels of rectangle luminance picture block are carried out taking mean operation to obtain luminance pixel row.Can
Selection of land, when carrying out mean filter, the size and the width phase of rectangle colourity image block or rectangle luminance picture block of filter window
Together.As shown in Fig. 2 (b), the rectangle frame in Fig. 2 (b) represents rectangle colourity image block or rectangle luminance picture block, by rectangle
Frame is averaged per one-row pixels can obtain a row pixel (see right vertical line in figure), and the row pixel is chroma pixel
Row or luminance pixel row.
S3：Variance yields, average and the kurtosis value arranged according to each chroma pixel of each two field picture calculates colourity saliency value,
And using the anglec of rotation corresponding to minimal color saliency value as the optimal colourity anglec of rotation, and according to each of each two field picture
The variance yields of luminance pixel row, average and kurtosis value calculate brightness saliency value, and by the anglec of rotation corresponding to minimum brightness saliency value
Degree is used as the optimal brightness anglec of rotation.
Wherein, colourity saliency value and brightness saliency value can be in step s3 and meanwhile obtain or in step
Successively obtained in S3.
In the present embodiment, the calculating formula of colourity saliency value and brightness saliency value is：
In the calculating formula, c is that chroma pixel arranges or luminance pixel row, σ (c) are chroma pixel row or luminance pixel row
Variance yields, μ (c) are that chroma pixel arranges or the average of luminance pixel row, κ (c) are the kurtosis of chroma pixel row or luminance pixel row
Value, sinh () is hyperbolic sine function.That is, if c arranges for chroma pixel, what is obtained is colourity saliency value；If
C arranges for luminance pixel, then what is obtained is brightness saliency value.
Because each two field picture will rotate repeatedly, each two field picture and its postrotational image have corresponding chroma pixel
Row and luminance pixel row, then each two field picture just has multiple chroma pixel row and multiple luminance pixels row, passes through the calculating formula
After calculating, each two field picture just has multiple colourity saliency value and multiple brightness saliency value, wherein, minimal color saliency value and minimum
The picture material that rectangle colourity image block and rectangle luminance picture block corresponding to the expression of brightness saliency value contain is most abundant, also
It is to say, rectangle colourity image block and rectangle luminance picture block may include the regions such as enteric cavity, intestinal mucosa simultaneously, so, most
The anglec of rotation corresponding to small colourity saliency value and minimum brightness saliency value just rotates for the optimal colourity anglec of rotation and optimal brightness
Angle.It should be noted that the optimal colourity anglec of rotation and the multiple that the optimal brightness anglec of rotation is unit angle, it is assumed that unit
Angle is 10 degree, and minimal color saliency value is obtains after image rotation 3 times, then the anglec of rotation corresponding to minimal color saliency value
It it is 6 times of unit angle for 60 degree.
S4：Each two field picture is rotated according to the optimal colourity anglec of rotation, it is vertical along picture centre line after rotation
The first rectangular image block is cut, and calculates the first difference value of the first rectangular image block on the chroma components, and by each frame
Image is rotated according to the optimal brightness anglec of rotation, vertically cuts the second rectangular image block along picture centre line after rotation,
And the second difference value of the second rectangular image block is calculated on the chroma components.
Wherein, although each two field picture is revolved according to the optimal colourity anglec of rotation and the optimal brightness anglec of rotation respectively
Turn, but be all to be calculated on the chroma components when the first difference value and the second difference value.First difference value and the second difference
Value can be in step s3 and meanwhile obtain or successively obtain in step s3.
In the present embodiment, the step of the first difference value for calculating the first rectangular image block on the chroma components is specially：
The first Euclidean distance of the chroma histogram of the first rectangular image block top half and the latter half is calculated, by the first Euclidean distance
It is quantified as the first difference value；The step of the second difference value for calculating the second rectangular image block on the chroma components is specially：Calculate
Second Euclidean distance of the chroma histogram of the second rectangular image block top half and the latter half, the second Euclidean distance is quantified
For the second difference value.Because Euclidean distance is bigger, the vision difference of image is bigger, therefore the difference value of image is bigger.Pass through
First Euclidean distance and the second Euclidean distance are quantified, you can obtain the first difference value and the second difference value.
S5：The first difference value and the second difference value of each two field picture are compared, and counts the first difference value and is more than
First frame number of the image of the second difference value and the second difference value are more than the second frame number of the image of the first difference value.
Wherein, the first difference value is more than the second difference value, represents preferably and rotates image using the optimal colourity anglec of rotation,
First difference value is less than the second difference value, represents preferably using optimal brightness anglec of rotation rotation image.
S6：If the first frame number is more than the second frame number, each two field picture is rotated according to the optimal colourity anglec of rotation,
If the second frame number is more than the first frame number, each two field picture is rotated according to the optimal brightness anglec of rotation.
Wherein, by counting the first frame number and the second frame number, can react the image of video on the whole should use most
The good colourity anglec of rotation rotate or should rotated using the optimal brightness anglec of rotation.
S7：Pixel column is vertically cut along picture centre line after the rotation of each two field picture, by the pixel column of each two field picture
Merge generation overview.
Wherein, after the optimal colourity anglec of rotation or the optimal brightness anglec of rotation determine, because each two field picture is according to most
The good brightness anglec of rotation is rotated, and the content representated by pixel column cut after rotation is with regard to more satisfactory.Referring to Fig. 3,
Fig. 3 (a) represents to cut the schematic diagram of pixel column, as seen from the figure, the pixel column cut using prior art using prior art
(white line in figure) is fully fallen on intestinal mucosa, without covering enteric cavity；And Fig. 3 (b) represents to apply the embodiment of the present invention
The schematic diagram scanned drawing generating method and cut pixel column, as seen from the figure, drawing generating method is scanned using the embodiment of the present invention
The pixel column (white line in figure) cut all covers enteric cavity and intestinal mucosa all the time.
Overview can reflect that alimentary canal tens to the integral status of tens of thousands of images, is scanned by being generated after step S7
Figure can accurately be shown gastral whole whether for the enteron aisle image that slag is mixed containing food or normal enteron aisle image
Body situation, that is, the size in region shared by the enteric cavity and enteric cavity of enteron aisle can be clearly displayed.Referring to Fig. 4, Fig. 4 (a) is one
The image pattern of enteron aisle of the group containing swill, Fig. 4 (b) are the overview generated using prior art, and as seen from the figure, this is vertical
Figure of looking at can not be shown without the intestinal mucosa region occupied by swill；Fig. 4 (c) is scanning using the embodiment of the present invention
The overview of drawing generating method generation, as seen from the figure, the enteron aisle that the overview can be shown without being occupied by swill sticks
Diaphragm area, the intestinal mucosa region concentrate on the lower zone of overview.
Further, referring to Fig. 5, Fig. 5 (a) is the image pattern of one group of normal bowel, and Fig. 5 (b) is using prior art
The overview of generation, as seen from the figure, the overview can not show that enteron aisle contains enteric cavity；Fig. 5 (c) is using the embodiment of the present invention
The overview of drawing generating method generation is scanned, as seen from the figure, the overview can not only show that enteron aisle contains enteric cavity, can also be clear
The size in enteric cavity shared region in enteron aisle is shown to Chu, the enteric cavity is formed in the intermediate region of overview.
By the above-mentioned means, the alimentary canal capsule endoscope video of the embodiment of the present invention scan drawing generating method pass through by
After image carries out multiple rotary, the optimal colourity anglec of rotation of image and optimal bright is determined respectively in colourity and luminance component
The anglec of rotation is spent, then selects most suitable angle to enter image from the optimal colourity anglec of rotation and the optimal brightness anglec of rotation
Row rotation, finally vertically cut pixel column per two field picture from according to the angle is postrotational along picture centre line and merge generation
Overview, so as to accurately show gastral integral status, and obtained overview can improve enteric cavity, gastrointestinal mucosa
Deng the indication range of alimentary canal viewing area, diagnosis efficiency of the doctor to alimentary canal capsule endoscope video is improved, reduces digestion
Fail to pinpoint a disease in diagnosis road viewing area.
Embodiments of the invention are the foregoing is only, are not intended to limit the scope of the invention, it is every to utilize this hair
The equivalent structure or equivalent flow conversion that bright specification and accompanying drawing content are made, or directly or indirectly it is used in other related skills
Art field, is included within the scope of the present invention.
Claims (6)
1. a kind of alimentary canal capsule endoscope video scans drawing generating method, it is characterised in that including：
S1：After each two field picture of video is transformed into hsv color space, each two field picture is carried out repeatedly around image center
The rotation of unit angle, wherein, the repeatedly unit angle sum is 180 degree；
S2：Rectangle is vertically cut along picture centre line on colourity H components to each two field picture and its each postrotational image
Colourity image block, and mean filter is carried out to rectangle colourity image block and obtains chroma pixel row, and to each two field picture and its
Each postrotational image vertically cuts rectangle luminance picture block on brightness V component along picture centre line, and to rectangle brightness
Image block carries out mean filter and obtains luminance pixel row；
S3：Variance yields, average and the kurtosis value arranged according to each chroma pixel of each two field picture calculates colourity saliency value, and will
The anglec of rotation corresponding to minimal color saliency value is as the optimal colourity anglec of rotation, and each brightness according to each two field picture
Variance yields, average and the kurtosis value of pixel column calculate brightness saliency value, and the anglec of rotation corresponding to minimum brightness saliency value is made
For the optimal brightness anglec of rotation；
S4：Each two field picture is rotated according to the optimal colourity anglec of rotation, vertically cut along picture centre line after rotation
First rectangular image block, and calculate the first difference value of the first rectangular image block on the chroma components, and by each two field picture
Rotated according to the optimal brightness anglec of rotation, vertically cut the second rectangular image block along picture centre line after rotation, and
The second difference value of the second rectangular image block is calculated on chromatic component；
S5：The first difference value and the second difference value of each two field picture are compared, and counts the first difference value and is more than second
First frame number of the image of difference value and the second difference value are more than the second frame number of the image of the first difference value；
S6：If the first frame number is more than the second frame number, each two field picture is rotated according to the optimal colourity anglec of rotation, if
Second frame number is more than the first frame number, and each two field picture is rotated according to the optimal brightness anglec of rotation；
S7：Pixel column is vertically cut along picture centre line after the rotation of each two field picture, the pixel column of each two field picture is carried out
Merge generation overview；
The calculating formula of the colourity saliency value and brightness saliency value is：
<mrow>
<mfrac>
<mn>1</mn>
<mrow>
<mi>&sigma;</mi>
<mrow>
<mo>(</mo>
<mi>c</mi>
<mo>)</mo>
</mrow>
<mo>+</mo>
<mn>1</mn>
</mrow>
</mfrac>
<mo>+</mo>
<mi>sinh</mi>
<mrow>
<mo>(</mo>
<mi>&mu;</mi>
<mo>(</mo>
<mi>c</mi>
<mo>)</mo>
<mo>)</mo>
</mrow>
<mo>+</mo>
<mi>sinh</mi>
<mrow>
<mo>(</mo>
<mi>&kappa;</mi>
<mo>(</mo>
<mi>c</mi>
<mo>)</mo>
<mo>)</mo>
</mrow>
</mrow>
Wherein, c is that chroma pixel arranges or luminance pixel arranges, and σ (c) is arranged for chroma pixel or the variance yields of luminance pixel row, μ (c)
For the average of chroma pixel row or luminance pixel row, κ (c) is that chroma pixel arranges or the kurtosis value of luminance pixel row, sinh () are
Hyperbolic sine function；
It is described calculate the first rectangular image block on the chroma components the first difference value the step of be specially：
The first Euclidean distance of the chroma histogram of the first rectangular image block top half and the latter half is calculated, by the first Euclidean
Distance is quantified as the first difference value；
It is described calculate the second rectangular image block on the chroma components the second difference value the step of specific calculate the second rectangular image
Second Euclidean distance of the chroma histogram of block top half and the latter half, the second difference is quantified as by the second Euclidean distance
Value.
2. alimentary canal capsule endoscope video according to claim 1 scans drawing generating method, it is characterised in that described
Unit angle is 5-15 degree.
3. alimentary canal capsule endoscope video according to claim 1 scans drawing generating method, it is characterised in that described
The height of rectangle colourity image block and rectangle luminance picture block is the height of image, the rectangle colourity image block and rectangle brightness
The width of image block is 9 or 11 pixel wides.
4. alimentary canal capsule endoscope video according to claim 3 scans drawing generating method, it is characterised in that is entering
During row mean filter, the size of filter window is identical with the width of rectangle colourity image block or rectangle luminance picture block.
5. alimentary canal capsule endoscope video according to claim 4 scans drawing generating method, it is characterised in that described
Carrying out the step of mean filter obtains chroma pixel row to rectangle colourity image block is specially：
Every one-row pixels of rectangle colourity image block are carried out taking mean operation to obtain chroma pixel row；
It is described to rectangle luminance picture block carry out mean filter obtain chroma pixel row the step of be specially：
Every one-row pixels of rectangle luminance picture block are carried out taking mean operation to obtain luminance pixel row.
6. alimentary canal capsule endoscope video according to claim 1 scans drawing generating method, it is characterised in that in step
Before rapid S1, in addition to：
Video is segmented sequentially in time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510894392.5A CN105468921B (en) | 2015-12-08 | 2015-12-08 | Alimentary canal capsule endoscope video scans drawing generating method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510894392.5A CN105468921B (en) | 2015-12-08 | 2015-12-08 | Alimentary canal capsule endoscope video scans drawing generating method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105468921A CN105468921A (en) | 2016-04-06 |
| CN105468921B true CN105468921B (en) | 2018-01-23 |
Family
ID=55606612
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510894392.5A Expired - Fee Related CN105468921B (en) | 2015-12-08 | 2015-12-08 | Alimentary canal capsule endoscope video scans drawing generating method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105468921B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0260883A2 (en) * | 1986-09-12 | 1988-03-23 | International Business Machines Corporation | Method for rotating an image |
| CN102419793A (en) * | 2010-09-28 | 2012-04-18 | 富士胶片株式会社 | Image processing apparatus and method, computer executable program, and radiation imaging system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9384528B2 (en) * | 2014-05-28 | 2016-07-05 | EchoPixel, Inc. | Image annotation using a haptic plane |
-
2015
- 2015-12-08 CN CN201510894392.5A patent/CN105468921B/en not_active Expired - Fee Related
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0260883A2 (en) * | 1986-09-12 | 1988-03-23 | International Business Machines Corporation | Method for rotating an image |
| CN102419793A (en) * | 2010-09-28 | 2012-04-18 | 富士胶片株式会社 | Image processing apparatus and method, computer executable program, and radiation imaging system |
Non-Patent Citations (2)
| Title |
|---|
| 内窥镜影像系统设计及图像处理的研究;岳泉;《中国优秀硕士学位论文全文数据库》;20070815(第2期);全文 * |
| 无线胶囊内窥镜图像处理技术研究;付延安;《中国博士学位论文全文数据库》;20131015(第10期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105468921A (en) | 2016-04-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11900623B2 (en) | Hyperspectral imaging with tool tracking in a light deficient environment | |
| US11727542B2 (en) | Super resolution and color motion artifact correction in a pulsed hyperspectral, fluorescence, and laser mapping imaging system | |
| CN104658014B (en) | A kind of method for detecting colorimetric abnormality in organism | |
| US7194118B1 (en) | System for optically sectioning and mapping surgically excised tissue | |
| CN105324064B (en) | Generate the method and apparatus for showing biomass density distributed image in biological tissue | |
| US20120113239A1 (en) | System and method for displaying an image stream | |
| US20150334276A1 (en) | System and method for displaying an image stream | |
| EP2286714A3 (en) | Detection of endoscope inserting direction | |
| CN103198501A (en) | Tooth panoramic picture automatic reconstruction method | |
| US20150320299A1 (en) | System and method for displaying an image stream | |
| US11288772B2 (en) | Super resolution and color motion artifact correction in a pulsed fluorescence imaging system | |
| EP1650982A1 (en) | Electronic endoscope apparatus | |
| US20140118586A1 (en) | Imaging apparatus | |
| US9561007B2 (en) | X-ray diagnostic apparatus | |
| CN105468921B (en) | Alimentary canal capsule endoscope video scans drawing generating method | |
| CN112654282B (en) | Medical image processing device, medical image processing method, endoscope system, and recording medium | |
| JPS63274911A (en) | Electronic endoscope device | |
| CN2708835Y (en) | Iris scanning detecting instrument | |
| CN112488945A (en) | Endoscope image enhancement method based on local convergence | |
| Al-youzbaki | Comparing the Process of Stitching Output Images from Colored and Un-colored Ultrasound Doppler Devices | |
| CN117764847A (en) | Method and system for focusing white light image and fluorescent image of 3D endoscope | |
| CN113225479A (en) | Data acquisition display system and image display method | |
| CN116416255A (en) | Image enhancement method, device, electronic device and storage medium | |
| Clarenz et al. | Colour Images |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20180123 Termination date: 20181208 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |