Dear Aditya

I will summarize for you briefly what you should do:-

Just go for any research engine (Google) and search for:-

" The Multiple Object recognition*.thesis"       download all the thesis on a folder

"The Multiple Object recognition*.thesis*.pptx"   download all the power points on a folder

"The Multiple Object recognition*.matlab codes"   download all codes on a folder

"The Multiple Object recognition*.pdf"       download all pdfs on a folder

"The Multiple Object recognition*.books"   download all books on a folder

you have just gathered all the material on the literature:- you should carry out the following steps:-

1 ) Read carefully what you have gathered on the previous folders.

2) Concentrate on what has been done and what on the future research, novel trends..

3) stoic on one of the problems pointed out  on the future work and the novel trends , formulate it and try to find the solution.

The outlines mentioned above will help you to build a good base for the subject and will make the research process is sequential.

Prof. S. EL-Rabaie

You must be lucky if you get some latest survey paper of your specific field, published in reputed journal. For example, see following conference paper i.e. Survey on Object Recognition:

"A survey on object recognition and segmentation techniques", 3rd International Conference on Computing for Sustainable Global Development (INDIACom), 2016.

You may also try Google Scholar for latest survey papers. You will get a jump start and a quick background/progress made in your respective field of research.

Good luck.

Engr. M. Muzammil

PhD Scholar

Thank you so much for your suggestions.

Dear aditya sk 

Prof. S. EL-Rabaie has summarized the research method Superbly. Also i recommended you with some sites will  help you in the reseach to obtain most of  papers which are not free.

http://sci-hub.cc/

http://www.sci-hub.ac/

http://bookzz.org/

http://booksc.org/

Hello Aditya,

What are the Objects you want to recognise ? Are they same object? and more in Number?

Example : 1st Case : You want to Detect Multiple objects of same class .

You want to detect Multiple Oranges in a Picture.

2nd Case : Multi Class Object detection

You want to detect Oranges, Apples, Banana's . 

If you are looking for the first case, it should not be that hard to implement, Apply the object detector multiple times on the images, instead returning when you find the first object.

If its the second case, try building feature detectors for every class and apply every detector onto the image to find the different objects.

In general there are many approaches to recognise the object. Simple features like Color, Shape, or more complex features using HaarWavelets.

Start with one object and move to multiple object recognition

Key point point detector based object recognition like SIFT, ORB and etc., Take the samples of different object and extract the features using SIFT, perform the feature matching between gallery and probe using FLANN.