6533b7dbfe1ef96bd1270c19

RESEARCH PRODUCT

PORE Algorithm for Object Recognition in Photo Layers based on Parametric Characteristics of the Object Edges

subject

description

PORE stands for Photo-Object Recognition based on the Edges. Coincidentally, PORE means to examine something carefully and with due attention, so "we pore over the object layers in search for information about their characteristics with the aim at improving image recognition process". Therefore, this study presents a novel approach to object recognition based on the pattern by using photo layers and by defining the objects' specific characteristics. We select and introduce the parameters which determine a higher efficiency of image retrieval of the image objects. In this paper, we describe how the same photos are recognized in a process of classical retrieval compared to our model by analyzing two prototypes; one grounded on the number of pixels, while in another one the objects are recognized by computing the number of shapes. In addition, we optimize our algorithm by using similarity attributes of some shapes. Such methodology empowers pattern recognition-based searching process with a very precise identification of the rotated objects, which are hardly ever retrieved by the most search engines. Even if so, the matching seems incidental, which does not influence the overall efficiency of the particular search system. From this perspective, our algorithm outperforms other object recognition approaches and can be applied to other image processing systems.