1

Topic: Pattern recognition on

The colleagues, What algorithms  in  for object detection. In particular it is necessary to find out persons and to highlight squares. I so suppose that convolution neural networks here do not approach because of weakness of iron. I.e. fastrcnn, squyzeenet not ? And that ? And yes I know that there is a heap of libraries with detection of persons. It is interesting to me as approximately they are made. The task at me  another, but too is connected to detection of subjects.

2

Re: Pattern recognition on

Hello, Gattaka, you wrote: G> colleagues, G> What algorithms  in  for object detection. In particular it is necessary to find out persons and to highlight squares. I so suppose that convolution neural networks here do not approach because of weakness of iron. I.e. fastrcnn, squyzeenet not ? And that ? And yes I know that there is a heap of libraries with detection of persons. It is interesting to me as approximately they are made. The task at me  another, but too is connected to detection of subjects. Like already and on  learned - here tells  Nuzhny much more. It already resulted any links.

3

Re: Pattern recognition on

Hello, Gattaka, you wrote: G> What algorithms  in  for object detection. In particular it is necessary to find out persons and to highlight squares. I so suppose that convolution neural networks here do not approach because of weakness of iron. I.e. fastrcnn, squyzeenet not ? And that ? And yes I know that there is a heap of libraries with detection of persons. It is interesting to me as approximately they are made. The task at me  another, but too is connected to detection of subjects. , pattern recognition works only for some classes of objects: persons, autonumbers, markers, geometrical objects. As soon as you need to start to recognize something another, you find out that there cinema and Germans.

4

Re: Pattern recognition on

Hello, Gattaka, you wrote: G> colleagues, G> What algorithms  in  for object detection. In particular it is necessary to find out persons and to highlight squares. I so suppose that convolution neural networks here do not approach because of weakness of iron. In cameras too iron so-so, but works.

5

Re: Pattern recognition on

6

Re: Pattern recognition on

P> Bugaga, pattern recognition works only for some classes of objects: persons, autonumbers, markers, geometrical objects. As soon as you need to start to recognize something another, you find out that there cinema and Germans. I remember  with the translator. Like from Google. I do not remember already. There there is a camera mode. You direct on an inscription on any object, translates words and phrases if it can be hooked for a phrase (hands if do not shiver) and besides, it replaces an inscription with the translated. And selects the same font and the size. It was ridiculous posters to translate from Russian into English. But basically a piece absolutely not necessary. It was played and used in a normal mode

7

Re: Pattern recognition on

8

Re: Pattern recognition on

Hello, Gattaka, you wrote: G> Thanks for the detailed review. I so understood from the task depends much. I.e. for  persons  these algorithms, and we tell for search of seals on aerial photographs already others. My task is very similar on  car numbers. Here algorithm   ? absolutely other algorithms ? to dig for ? Yes, depends on the task much. The method of Violy-Dzhonsa about usage of features of Haar (Haar features) works so well on persons because they have an accurate structure in respect of areas: the forehead is more light, eye-sockets are more dark, the nose too is more light, etc. If we take the task of detection of people (pedestrians) this detector starts to work worse than ever because in a human figure it is more important not than area, and its circuits. About 15 years ago other approach - HOG + linear SVM here "shot". It works actually with circuits (with gradients, it is finite) also not ideally, but it is already much better. Mentioned by me above DPM is more generalized version classical HOG, dlib uses the similar approach for persons and pedestrians, receives better quality at comparable speed of operation. It is called at them FHOG. As classical HOG, and FHOG were checked on car numbers of the small size (from 20 to 100 pixels in height), work very well. It from fast classical methods. Generalization HOG also is ICF (Integral channels features + boosting trees forest) which on the same pedestrians receive better quality, but work noticeably more slowly. Here it is used except HOG also colors (here in what a quality secret), but the approach demands large multisequencing, suits only architecture of type of videocards. There are separate methods for text detection in a frame. They differ from the aforesaid. P.S. But now on  are actively used and , Tensor flow not only that  under Android so also it is included in basic delivery in its last version. I would not began to sweep aside them if conditions allow. But here not to me, I in the last novelties  the small expert.

9

Re: Pattern recognition on

Hello, Gattaka, you wrote: Tensorflow Android Camera Demo