阅读说明：本技术 寄生虫虫卵图像特征选择方法 (Parasite egg pictures feature selection approach ) 是由 刘小英 于 2018-05-16 设计创作，主要内容包括：本发明公开了寄生虫虫卵图像特征选择方法,涉及寄生虫虫卵特征选择,包括寄生虫虫卵样本图像,还包括以下步骤：S1,进行图像去噪处理后,对所述寄生虫虫卵样本图像进行图像信息统计,获得基本统计特征集；S2,获取基于图像自身属性的特征点集；S3,获取区域定义的特征点集；S4,依据S1-S3获取的特征集,计算每个特征集子项的方差,并选取方差最小的6个特征,再将6个特征采用特征压缩方法进行降维,形成3个描述特征作为图像的特征,作为寄生虫虫卵图像的特征参数。本发明通过选择合适的特征,能够有效提高寄生虫虫卵图像特征选择的稳定性、精确性及实时性；能够综合考虑不同条件下的特征有效性,提高图像特征的抗干扰能力。(The invention discloses parasite egg pictures feature selection approach, it is related to parasite egg feature selecting, including parasite egg sample image, it is further comprising the steps of: S1, after carrying out image denoising processing, image information statistics is carried out to the parasite egg sample image, obtains basic statistics feature set；S2 obtains the feature point set based on image self attributes；S3 obtains the feature point set that region defines；S4 calculates the variance of each feature set subitem according to the feature set that S1-S3 is obtained, and choose the smallest 6 features of variance, 6 features are subjected to dimensionality reduction using Feature Compression method again, form feature of 3 Expressive Features as image, the characteristic parameter as parasite egg pictures.The present invention can effectively improve the stability, accuracy and real-time of parasite egg pictures feature selecting by selecting suitable feature；The characteristic validity under different condition can be comprehensively considered, improve the anti-interference ability of characteristics of image.)

1. parasite egg pictures feature selection approach, including parasite egg sample image, which is characterized in that further include following Step:

S1 after carrying out image denoising processing, carries out image information statistics to the parasite egg sample image, obtains basic system Count feature set；

S2 obtains the feature point set based on image self attributes；

S3 obtains the feature point set that region defines；

S4 calculates the variance of each feature set subitem, and choose the smallest 6 spies of variance according to the feature set that S1-S3 is obtained Sign, then 6 features are subjected to dimensionality reduction using Feature Compression method, feature of 3 Expressive Features as image is formed, as parasitism The characteristic parameter of worm worm's ovum image.

2. parasite egg pictures feature selection approach according to claim 1, which is characterized in that the region defined Feature point set, including LOG operator, Forstner operator, SIFT operator.

3. parasite egg pictures feature selection approach according to claim 1, which is characterized in that described to be belonged to based on itself The feature point set of property, including marginal point, angle point, crosspoint.

4. parasite egg pictures feature selection approach according to claim 1, which is characterized in that the basic statistics is special Sign, including brightness, center of gravity, grey level histogram.

5. parasite egg pictures feature selection approach according to claim 1, which is characterized in that the Feature Compression side For method using in first 6 of minimum variance ranking, ranking is that the feature of odd number is multiplied with the feature of its latter position, forms new spy Sign.

Technical field

The present invention relates to parasite egg feature selectings, and in particular to parasite egg pictures feature selection approach.

Background technique

Parasite of human refers to the helminth using people as host.Endophyte worm and epizoon two major classes can be divided into. Belong to protozoan, round worm, flatworm, annelid and arthropod mostly.Traditionally primary dynamic in parasitology Object is known as protozoon class, and round worm and flatworm are collectively referred to as Vermes.The important type of endophyte worm includes mostly In protozoon class, Nemata, Trematoda and tapeworms.Studying parasite egg has important meaning to medical students ' learning and guidance Justice.That there are distracters is more for parasite egg pictures at present, it is difficult to the problem of selecting good identification feature.

Summary of the invention

The technical problem to be solved by the present invention is to current parasite egg pictures, that there are distracters is more, it is difficult to which selection is good The problem of identification feature, and it is an object of the present invention to provide parasite egg pictures feature selection approach, solves the above problems.

The present invention is achieved through the following technical solutions:

Parasite egg pictures feature selection approach, including parasite egg sample image, further comprising the steps of:

S1 after carrying out image denoising processing, carries out image information statistics to the parasite egg sample image, obtains base This statistical nature collection；

S2 obtains the feature point set based on image self attributes；

S3 obtains the feature point set that region defines；

S4 calculates the variance of each feature set subitem, and it is 6 the smallest to choose variance according to the feature set that S1-S3 is obtained Feature, then 6 features are subjected to dimensionality reduction using Feature Compression method, feature of 3 Expressive Features as image is formed, as posting The characteristic parameter of infested worm's ovum image.

Further, the feature point set that the region defines, including LOG operator, Forstner operator, SIFT operator.

Further, the feature point set based on self attributes, including marginal point, angle point, crosspoint.

Further, the basic statistics feature, including brightness, center of gravity, grey level histogram.

Further, the Feature Compression method is using in first 6 of minimum variance ranking, ranking be odd number feature with The feature of its latter position is multiplied, and forms new feature.

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

1, parasite egg pictures feature selection approach of the present invention can be effectively improved and be posted by selecting suitable feature Stability, accuracy and the real-time of infested worm's ovum image feature selection；

2, parasite egg pictures feature selection approach of the present invention, the feature that can be comprehensively considered under different condition are effective Property, improve the anti-interference ability of characteristics of image.

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.