KR20110116841A - Analysis system of red tide image using wavelet transformation - Google Patents

Analysis system of red tide image using wavelet transformation Download PDF

Info

Publication number
KR20110116841A
KR20110116841A KR1020100036490A KR20100036490A KR20110116841A KR 20110116841 A KR20110116841 A KR 20110116841A KR 1020100036490 A KR1020100036490 A KR 1020100036490A KR 20100036490 A KR20100036490 A KR 20100036490A KR 20110116841 A KR20110116841 A KR 20110116841A
Authority
KR
South Korea
Prior art keywords
red tide
image
color value
analysis
processing module
Prior art date
Application number
KR1020100036490A
Other languages
Korean (ko)
Inventor
송병호
이성로
이연우
정민아
Original Assignee
목포대학교산학협력단
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 목포대학교산학협력단 filed Critical 목포대학교산학협력단
Priority to KR1020100036490A priority Critical patent/KR20110116841A/en
Publication of KR20110116841A publication Critical patent/KR20110116841A/en

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K9/00Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
    • G06K9/36Image preprocessing, i.e. processing the image information without deciding about the identity of the image
    • G06K9/40Noise filtering
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K9/00Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
    • G06K9/36Image preprocessing, i.e. processing the image information without deciding about the identity of the image
    • G06K9/46Extraction of features or characteristics of the image
    • G06K9/4652Extraction of features or characteristics of the image related to colour
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/40Analysis of texture
    • G06T7/41Analysis of texture based on statistical description of texture
    • G06T7/42Analysis of texture based on statistical description of texture using transform domain methods
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K9/00Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
    • G06K9/36Image preprocessing, i.e. processing the image information without deciding about the identity of the image
    • G06K9/46Extraction of features or characteristics of the image
    • G06K9/48Extraction of features or characteristics of the image by coding the contour of the pattern contour related features or features from contour like patterns, e.g. hand-drawn point-sequence
    • G06K2009/488Extraction of features or characteristics of the image by coding the contour of the pattern contour related features or features from contour like patterns, e.g. hand-drawn point-sequence using wavelet analysis
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/20Special algorithmic details
    • G06T2207/20048Transform domain processing
    • G06T2207/20064Wavelet transform [DWT]

Abstract

The present invention discloses a red tide image analysis system using wavelet transform. In accordance with an aspect of the present invention, a red tide image analysis system includes: a preprocessing module configured to output a corrected image by removing noise when receiving an image photographed for a resolution; A processing module for extracting a color value from the corrected image and detecting a red tide occurrence area using the color value; And an interface module for displaying the detected red tide occurrence area and its movement path.

Description

Analysis System of Red Tide Image using Wavelet Transformation

The present invention relates to a system for detecting red tide generation, and more particularly, to a red tide image analysis system using wavelet transform capable of predicting whether red tide occurs using an image photographed for the sea.

Generally, red tide occurs at sea, causing serious damage, such as the inflow of seawater into the farming brood and the death of farmed fish and shellfish.

Indeed, from September 1995 to October, there were continuous red tide on the south and east coasts of Korea, resulting in over 70 billion damages to the farms, and since then, red tide has been increasing in Korea.

Therefore, physical and chemical methods for reducing damage caused by red tide are being studied in Japan and the United States, and a method of managing seawater through sensors has already been used.

However, since the causes of red tide are very diverse, it is very difficult to determine whether red tide has occurred at sea.

The present invention has been made in the technical background as described above, and the red tide image analysis system using the wavelet transform that can predict the red tide occurrence region and its moving path by the image information detected by applying the wavelet transform to the image photographed for the sea To provide that purpose.

Another object of the present invention is to provide a red tide image analysis system using wavelet transform that can display and display a red tide occurrence region and its moving path by applying a classification algorithm to image information of an image photographed at sea.

In accordance with an aspect of the present invention, a red tide image analysis system includes: a preprocessing module configured to output a corrected image by removing noise when receiving an image photographed for a resolution; A processing module for extracting a color value from the corrected image and detecting a red tide occurrence area using the color value; And an interface module for displaying the detected red tide occurrence area and its movement path.

Here, the processing module extracts the color value from the corrected image using wavelet transformation, and detects the red tide occurrence region by applying a support vector machine (SVM) algorithm to the color value. Can be.

According to the present invention, it is possible to increase the accuracy of acquiring image information by removing the noise of the image taken for the sea, and extracting the spatial feature of the image, that is, image information by applying wavelet transform to the image from which the noise is removed, This can be used to predict the area of red tide.

In addition, the present invention can be displayed while tracking the red tide occurrence region and its moving path by applying a classification algorithm to the extracted image information, it is possible to prevent the red tide has a serious effect on the marine environment.

1 is a block diagram showing a red tide image analysis system according to an embodiment of the present invention.
2 is a flowchart illustrating a red tide image analyzing method according to an exemplary embodiment of the present invention.

Advantages and features of the present invention and methods for achieving them will be apparent with reference to the embodiments described below in detail with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but will be implemented in various forms, and only the present embodiments are intended to complete the disclosure of the present invention, and the general knowledge in the art to which the present invention pertains. It is provided to fully convey the scope of the invention to those skilled in the art, and the present invention is defined only by the scope of the claims. It is to be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. In the present specification, the singular form includes plural forms unless otherwise specified in the specification. As used herein, “comprises” and / or “comprising” refers to a component, step, operation and / or device that is present in one or more other components, steps, operations and / or elements. Or does not exclude additions.

The present invention extracts spatial features of an image by applying wavelet transform to an image photographed for resolution. In detail, by transforming the image data into the frequency domain by moving and extending the base function through the wavelet transform, and analyzing the subbands in the frequency domain, the image information (color, shape, texture, etc.) for the image Can be extracted.

In this case, each pixel of the extracted image is composed of RGB colors, and since each of the RGB elements is too large in correlation, when the red tide occurrence region is detected using RGB information, the red tide occurrence region is likely to be incorrectly detected.

Therefore, in the present invention, the red tide occurrence area of the sea is detected by using the color value of the HSI color model that recognizes the image information as Hue, Saturation, and Lightness.

Preferred embodiments of the present invention will now be described in detail with reference to the accompanying drawings. 1 is a block diagram showing a red tide image analysis system according to an embodiment of the present invention.

As shown in FIG. 1, the red tide image analysis system 10 includes a preprocessing module 100, a processing module 200, and a user interface module 300.

The preprocessing module 100 removes noise from the image obtained by using the noise removing filter, and outputs the corrected image as a result. Here, the acquired image is an image of the satellite imaged the sea, the preprocessing module 100 receives the image from the satellite in a direct or indirect manner.

The processing module 200 extracts image information such as color, shape, and texture from the image corrected using the wavelet transform, and the color (Hue) from the color values (R, G, B values) using Equation 1 below. ) To extract the value. In Equation 1 below, R, G, and B are color values (RGB values) of image information.

Figure pat00001

The processing module 200 detects a red tide occurrence area by applying a support vector machine (SVM) algorithm to the extracted color value.

Here, the SVM algorithm converts a given problem into a convex quadratic problem, which guarantees a global optimal solution. Therefore, the SVM algorithm shows an excellent performance in the field of pattern recognition, and is optimal among many linear classification functions. The classification function of can be chosen to provide an optimal separation interface that separates the given data into two groups as far as possible. Therefore, the processing module 200 may effectively detect the red tide occurrence region, which is a red region, from the entire region of the image using the SVM algorithm.

The user interface module 300 displays the red tide occurrence area detected by the processing module 200 to the user. At this time, the red tide image analysis system 10 receives an image photographed at a predetermined time interval and detects a red tide occurrence region from the red tide image analysis system 10, so that the red tide image analysis system 10 may track and display the red tide movement path generated at the predetermined time interval.

On the other hand, if the red tide generation area is not detected by the processing module 200, the user interface module 300 may indicate that red tide has not occurred, or may not perform the display.

Hereinafter, a red tide image analysis method according to an exemplary embodiment of the present invention will be described with reference to FIG. 2. 2 is a flowchart illustrating a method of analyzing red tide images according to an exemplary embodiment of the present invention.

Referring to FIG. 2, the red tide image analysis system 10 monitors whether an image photographed for sea resolution is received from a satellite (S210).

If the captured image is received, the red tide image analysis system 10 outputs a corrected image by removing noise of the received image (S220).

Next, the red tide image analysis system 10 detects a red tide occurrence region from the corrected image (S230). In detail, the red tide image analysis system 10 may obtain a color value from the image corrected through the wavelet transform, and detect the red tide occurrence region by applying an SVM algorithm to the color value.

The red tide image analysis system 10 displays the detected red tide occurrence area, if there is a detected red tide occurrence area (YES in S240) (S250). In addition, the red tide image analysis system 10 displays the extended area of the detected red tide occurrence area and the movement path thereof.

On the other hand, if the red tide image analysis system 10 does not have a detected red tide occurrence region (No in S240), it indicates that there is no red tide occurrence region or detects the red tide occurrence region for the received image without performing a separate display. Steps (S210) to (S240) may be repeated.

As described above, the present invention can improve the accuracy of image information acquisition by removing the noise of the image taken for the sea, and extract the spatial feature of the image, that is, the image information by applying the wavelet transform to the image from which the noise is removed. Using this method, the area of red tide can be predicted.

In addition, the present invention can be displayed while tracking the red tide occurrence region and its moving path by applying a classification algorithm to the extracted image information, it is possible to prevent the red tide has a serious effect on the marine environment.

While the present invention has been described in detail with reference to the accompanying drawings, it is to be understood that the invention is not limited to the above-described embodiments. Those skilled in the art will appreciate that various modifications, Of course, this is possible. Accordingly, the scope of protection of the present invention should not be limited to the above-described embodiments, but should be determined by the description of the following claims.

10: red tide image analysis system 100: preprocessing module
200: processing module 300: user interface module

Claims (2)

  1. A pre-processing module that outputs a corrected image by removing noise when receiving an image photographed for resolution;
    A processing module for extracting a color value from the corrected image and detecting a red tide occurrence area using the color value; And
    Interface module for displaying the detected red tide occurrence region and its movement path
    Red tide image analysis system comprising a.
  2. The method of claim 1, wherein the processing module,
    And extracting the color value from the corrected image using a wavelet transformation, and detecting the red tide occurrence region by applying a support vector machine (SVM) algorithm to the color value.
KR1020100036490A 2010-04-20 2010-04-20 Analysis system of red tide image using wavelet transformation KR20110116841A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
KR1020100036490A KR20110116841A (en) 2010-04-20 2010-04-20 Analysis system of red tide image using wavelet transformation

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
KR1020100036490A KR20110116841A (en) 2010-04-20 2010-04-20 Analysis system of red tide image using wavelet transformation

Publications (1)

Publication Number Publication Date
KR20110116841A true KR20110116841A (en) 2011-10-26

Family

ID=45031067

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1020100036490A KR20110116841A (en) 2010-04-20 2010-04-20 Analysis system of red tide image using wavelet transformation

Country Status (1)

Country Link
KR (1) KR20110116841A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103163420A (en) * 2011-12-08 2013-06-19 沈阳工业大学 Intelligent power transformer on-line state judgment method
CN103398769A (en) * 2013-08-05 2013-11-20 国家电网公司 Transformer on-line fault detecting method based on sampling integrated SVM (support vector machine) under wavelet GGD (general Gaussian distribution) feather and unbalanced K-mean value
CN105203876A (en) * 2015-09-15 2015-12-30 云南电网有限责任公司电力科学研究院 Transformer on-line monitoring state assessment method utilizing support vector machine and correlation analysis

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103163420A (en) * 2011-12-08 2013-06-19 沈阳工业大学 Intelligent power transformer on-line state judgment method
CN103398769A (en) * 2013-08-05 2013-11-20 国家电网公司 Transformer on-line fault detecting method based on sampling integrated SVM (support vector machine) under wavelet GGD (general Gaussian distribution) feather and unbalanced K-mean value
CN103398769B (en) * 2013-08-05 2014-12-31 国家电网公司 Transformer on-line fault detecting method based on sampling integrated SVM (support vector machine) under wavelet GGD (general Gaussian distribution) feather and unbalanced K-mean value
CN105203876A (en) * 2015-09-15 2015-12-30 云南电网有限责任公司电力科学研究院 Transformer on-line monitoring state assessment method utilizing support vector machine and correlation analysis

Similar Documents

Publication Publication Date Title
Rokni et al. A new approach for surface water change detection: Integration of pixel level image fusion and image classification techniques
Qi et al. A robust directional saliency-based method for infrared small-target detection under various complex backgrounds
CN103578116B (en) For tracking the apparatus and method of object
US8369652B1 (en) Visual attention system for salient regions in imagery
Davis et al. Robust Background-Subtraction for Person Detection in Thermal Imagery.
Ji et al. Robust video restoration by joint sparse and low rank matrix approximation
Verdoliva et al. A feature-based approach for image tampering detection and localization
US9158985B2 (en) Method and apparatus for processing image of scene of interest
US8878963B2 (en) Apparatus and method for noise removal in a digital photograph
Oliveira et al. Skin Detection using HSV color space
US7636454B2 (en) Method and apparatus for object detection in sequences
Wang et al. Recent advances in image dehazing
KR101023207B1 (en) Video object abstraction apparatus and its method
Pape et al. 3-D histogram-based segmentation and leaf detection for rosette plants
JP4480958B2 (en) Digital image creation method
JP5741447B2 (en) Image generation apparatus, image generation method, and image generation program
Fillion et al. Detecting content adaptive scaling of images for forensic applications
Qu et al. Detect digital image splicing with visual cues
WO2014032020A3 (en) Feature based high resolution motion estimation from low resolution images captured using an array source
KR101932543B1 (en) Method and Apparatus for detecting smoke from image
Ren et al. Fusion of intensity and inter-component chromatic difference for effective and robust colour edge detection
US8798373B2 (en) Image restoration system, image restoration method, and image restoration program
Cooper Improved photo response non-uniformity (PRNU) based source camera identification
US8923554B2 (en) Information processing device, recognition method thereof and non-transitory computer-readable storage medium
US8548247B2 (en) Image processing apparatus and method, and program

Legal Events

Date Code Title Description
WITN Withdrawal due to no request for examination