BRIEF HISTORY

Oxford Recognition Ltd is working in automated digital image processing, decision making and artificial intelligence. The director and the founder of the company Dr. D.Dubovitskiy has invented several new algorithms for digital image processing computer science. He has originated and applied for two patents as inventor. The algorithmic results embedded novel approach with extended repeatability and interoperability. The application focused on several interdisciplinary projects concerned biology, pharmacology, physiques and material industries and health care. The past experience has included the whole cycle of R&D projects from project coordinator for EU grant, adviser, consultant, instrumentation architect-developer and principal investigator.

The company has a background in producing image processing content for the UK Metropolitan Police specifically to recognize human face on dynamical backgrounds.  It delivered the demonstration MatLab/C++ project which involved London facial recognition. Another project was delivered to Metropolitan Police to protect security by use of encoded data into Fractal pattern which was printed on identity card. Within this technology, even if a person changed a photograph on a document to deceive, the fractal encoded picture remains the same, thereby identifying the alteration. The same technology  was tested for recognition of counterfeit passports, and international ID documents by use of a handheld device, without the requirement for large expensive machinery  or any specialist training.  We have knowledge of how the product could benefit the security and safety market. The image recognition development could also have many uses outside of these three environments.

The company is also deeply involved in the continued development of project involved in the design of a medical imaging system in order to screen and recognize abnormal biological cells in Cervical Smear test samples. The system uses microscopy with a motorized table. The sample is prepared utilising the Papanicolaou method and  then automatically scanned by a microscope which is capable of making a decision on whether the disease was present. Other activities of the company are related to pattern recognition based on fractal analysis in various applications. Since 2016, the company has started another activity devoted to the security issues: application of the fractal analysis to the pattern recognition and analysis of the scattering data from the neutron and X-ray scanning.

This technology was applied to the Cervical Smear recognition algorithm which is capable of automative decision making in other biological and interdisciplinary projects. For example, the skin cancer detection was sold as Moletest (www.wikipedia.org/wiki/Moletest). This project was focused on the use of the algorithm by GP doctors for evaluation of suspicious birth-marks or moles found on patients. The image acquisition was performed with a Nikon dermatology lens adapter and the structure recognition descriptors were designed in this case to push the decision-making engine to make an optimal-probabilistic conclusion for particular skin conditions.