阅读说明：本技术 用于污水偷排企业定位的图像识别方法 (Image-recognizing method for the positioning of sewage Tou Pai enterprise ) 是由 朱姝 于 2018-05-21 设计创作，主要内容包括：本发明公开了用于污水偷排企业定位的图像识别方法,涉及污水偷排企业图像识别,包括依据污水偷排企业设置的类别样本、待识别图像,还包括以下步骤：S1,获取来自依据污水偷排企业设置的采集点的待识别图像,在空间域中进行分解域变换,使图像信息分解到的多个尺度空间中；S2,利用空间域梯度算子进行待识别图像的边缘检测；S3,在图像变换域中,利用小波进行待识别图像的边缘检测；S4,提取空间域和变换域中边缘检测获取的待识别图像的特征向量；S5,利用人工神经网络进行模式识别。本发明能够有效提取依据污水偷排企业设置的背景的外部边缘,作为理想的特征；能够依据空间域和变换域双重检测,提高检测精度。(The invention discloses the image-recognizing methods positioned for sewage Tou Pai enterprise, it is related to sewage Tou Pai enterprise image recognition, including the classification sample according to the setting of sewage Tou Pai enterprise, images to be recognized, it is further comprising the steps of: S1, obtain the images to be recognized from the collection point according to the setting of sewage Tou Pai enterprise, decomposition field transformation is carried out in the spatial domain, in the multiple scale spaces for decomposing image information；S2 carries out the edge detection of images to be recognized using spatial domain gradient operator；S3 carries out the edge detection of images to be recognized using small echo in image transform domain；S4 extracts the feature vector for the images to be recognized that edge detection obtains in spatial domain and transform domain；S5 carries out pattern-recognition using artificial neural network.The present invention can effectively extract the external margin of the background according to the setting of sewage Tou Pai enterprise, as ideal feature；Detection accuracy can be improved according to spatial domain and transform domain double check.)

1. for sewage Tou Pai enterprise positioning image-recognizing method, including according to sewage Tou Pai enterprise setting classification sample, Images to be recognized, which is characterized in that further comprising the steps of:

S1 obtains the images to be recognized from the collection point according to the setting of sewage Tou Pai enterprise, carries out decomposition field in the spatial domain It converts, in the multiple scale spaces for decomposing image information；

S2 carries out the edge detection of images to be recognized using spatial domain gradient operator；

S3 carries out the edge detection of images to be recognized using small echo in image transform domain；

S4 extracts the feature vector for the images to be recognized that edge detection obtains in spatial domain and transform domain；

S5 carries out pattern-recognition using artificial neural network, the classification sample according to the setting of sewage Tou Pai enterprise is carried out offline Training, determines weight, carries out operation with the feature vector that S4 is obtained, realizes the identification of images to be recognized.

2. the image-recognizing method according to claim 1 for the positioning of sewage Tou Pai enterprise, which is characterized in that the S1 In decomposition field transformation using Multiscale Wavelet Decomposition domain convert.

3. the image-recognizing method according to claim 1 for the positioning of sewage Tou Pai enterprise, which is characterized in that the S2 In gradient operator use Gauss-Laplace.

4. the image-recognizing method according to claim 1 for the positioning of sewage Tou Pai enterprise, which is characterized in that the S3 In edge detection results recorded using chained list.

5. the image-recognizing method according to claim 1 for the positioning of sewage Tou Pai enterprise, which is characterized in that the S4 In feature vector use statistical nature.

Technical field

The present invention relates to sewage Tou Pai enterprise image recognitions, and in particular to the image recognition for the positioning of sewage Tou Pai enterprise Method.

Background technique

Sewage, which is stolen, to be arranged, and is referred to discharge, is toppled over or dispose active waste, is the waste containing infectious disease pathogens, toxic Substance or other harmful substances, the serious behavior for polluting environment.Sewage steals row's enterprise sort and is difficult to judge at present, it is difficult to accomplish Timely early warning.

Summary of the invention

It steals row's enterprise sort the technical problem to be solved by the present invention is to current sewage to be difficult to judge, it is difficult to accomplish pre- in time Police solves the above problems, and it is an object of the present invention to provide for the image-recognizing method that sewage Tou Pai enterprise positions.

The present invention is achieved through the following technical solutions:

It steals for the image-recognizing method of sewage Tou Pai enterprise positioning, including sewage and arranges enterprise sort sample, figure to be identified Picture, further comprising the steps of:

S1 obtains the images to be recognized from sewage Tou Pai enterprise collection point, carries out decomposition field transformation in the spatial domain, makes In multiple scale spaces that image information decomposes；

S2 carries out the edge detection of images to be recognized using spatial domain gradient operator；

S3 carries out the edge detection of images to be recognized using small echo in image transform domain；

S4 extracts the feature vector for the images to be recognized that edge detection obtains in spatial domain and transform domain；

S5 carries out pattern-recognition using artificial neural network, and sewage is stolen and arranges enterprise sort sample progress off-line training, really Determine weight, carries out operation with the feature vector that S4 is obtained, realize the identification of images to be recognized.

Further, the decomposition field transformation in the S1 is converted using Multiscale Wavelet Decomposition domain.

Further, the gradient operator in the S2 uses Gauss-Laplace.

Further, the edge detection results in the S3 are recorded using chained list.

Further, the feature vector in the S4 uses statistical nature.

Compared with prior art, the present invention having the following advantages and benefits:

1, image-recognizing method of the present invention for the positioning of sewage Tou Pai enterprise can effectively extract sewage Tou Pai enterprise back The external margin of scape, as ideal feature；

2, image-recognizing method of the present invention for the positioning of sewage Tou Pai enterprise, can be dual according to spatial domain and transform domain Detection improves detection accuracy.

Specific embodiment

To make the objectives, technical solutions, and advantages of the present invention clearer, below with reference to embodiment, the present invention is made Further to be described in detail, exemplary embodiment of the invention and its explanation for explaining only the invention, are not intended as to this The restriction of invention.