Multi-Class Classification and Multi-Output Regression of Three-Dimensional Objects Using Artificial Intelligence Applied to Digital Holographic Information.

Digital holographically sensed 3D data processing, which is useful for AI-based vision, is demonstrated. Three prominent methods of learning from datasets such as sensed holograms, computationally retrieved intensity and phase from holograms forming concatenated intensity-phase (whole information) images, and phase-only images (depth information) were utilized for the proposed multi-class classification and multi-output regression tasks of the chosen 3D objects in supervised learning. Each dataset comprised 2268 images obtained from the chosen eighteen 3D objects. The efficacy of our approaches was validated on experimentally generated digital holographic data then further quantified and compared using specific evaluation matrices. The machine learning classifiers had better AUC values for different classes on the holograms and whole information datasets compared to the CNN, whereas the CNN had a better performance on the phase-only image dataset compared to these classifiers. The MLP regressor was found to have a stable prediction in the test and validation sets with a fixed EV regression score of 0.00 compared to the CNN, the other regressors for holograms, and the phase-only image datasets, whereas the RF regressor showed a better performance in the validation set for the whole information dataset with a fixed EV regression score of 0.01 compared to the CNN and other regressors.

Recognition and classification of three-dimensional phase objects by digital Fresnel holography.

We demonstrate the validity of wavelet-based processing for recognition and classification of three-dimensional phase objects. One Fresnel digital hologram of each of the three-dimensional (3-D) phase objects to be classified is recorded. The electronic holograms are processed digitally to permit 3-D object information to be retrieved as two-dimensional digital complex images. We use a Mexican-hat wavelet- matched filter (WMF) to enhance the correlation peak and discriminate between the objects. The WMF performs a wavelet transform (WT) to enhance the significant features of the images and the correlation of the WT coefficients thus obtained. We compare the feasibility of a WMF-based object classifier with the matched-filter-based classifier to classify our four 3-D phase objects in a 3-D scene into true or false classes with minimal error.