To answer this question, you should define what is meant by object recognition. You can then include research evidence showing how object recognition is performed.
There are four current theoretical approaches to the representation and recognition of visual objects: structural descriptions, geometric constraints, multidimensional feature spaces, and shape-space approximation.
Have a look: https://www.sciencedirect.com/science/article/abs/pii/S1364661397010905
Pattern/object recognition is concerned with the processes involved in the identification of images and objects. This essentially involves taking information that enters the visual system and comparing this with information stored in memory, and finding a match. There are three approaches within pattern recognition; template and prototype theories, feature comparison theories and structural theories. The focus of this essay is feature comparison theories, their advantages and disadvantages and their overall success in pattern/object recognition.
any object regular or irregular in shape and size will have its own geometry when it comes to image processing, this can be solved by keras H5 model, pls refer our research work on H5 model.