We review two different techniques for visualization and processing of three-dimensional (3D) objects based on passive and active optical sensing. First, we describe the basis of a passive-sensing technique based on integral imaging. Also, we show that it is possible to improve the depth of field of this method by using amplitude-modulated microlens arrays. Second, we describe an active-sensing technique based on digital holography. Finally, we apply both techniques to de-velop 3D image processing applications. In particular, we design two different 3D pattern recognition techniques. Both of them are based in storing the 3D data in two-dimensional (2D) form. In this way, it is possible to recognize 3D objects by performing 2D correlations or applying neural network techniques. Experimental results are presented.