Research

Afaq's research interests are in 3D Feature Representation, 3D Object Recognition, 3D Modeling, Object Detection, Machine Learning and Deep Learning. He investigates the detection and recognition of objects in real environment scenes, and image understanding.

Efficient Image Set Classification using Linear Regression based Image Reconstruction

In this research, we proposed a novel image set classification technique using linear regression models. Downsampled gallery image sets are interpreted as subspaces of a high dimensional space to avoid the computationally expensive training step. We estimate regression models for each test image using the class specific gallery subspaces. Images of the test set are then reconstructed using the regression models. Based on the minimum reconstruction error between the reconstructed and the original images, a weighted voting strategy is used to classify the test set. We performed extensive evaluation on the benchmark UCSD/Honda, CMU Mobo and YouTube Celebrity datasets for face classification, and ETH-80 dataset for object classification. The results demonstrate that by using only a small amount of training data, our technique achieved competitive classification accuracy and superior computational speed compared with the state-of-the-art methods.

Iterative Deep Learning for Image set based Face and Object Recognition

In this project, we propose a novel technique for image set based face/object recognition, where each gallery and query example contains a face/object image set captured from different viewpoints, background, facial expressions, resolution and illumination levels. While several image set classification approaches have been proposed in recent years, most of them represent each image set as a single linear subspace, mixture of linear subspaces or Lie group of Riemannian manifold. These techniques make prior assumptions in regards to the specific category of the geometric surface on which images of the set are believed to lie. This could result in a loss of discriminative information for classification. This paper alleviates these limitations by proposing an Iterative Deep Learning Model (IDLM) that automatically and hierarchically learns discriminative representations from raw face and object images. In the proposed approach, low level translationally invariant features are learnt by the Pooled convolutional Layer (PCL). The latter is followed by Artificial Neural Networks (ANNs) applied iteratively in a hierarchical fashion to learn a discriminative non-linear feature representation of the input image sets. The proposed technique was extensively evaluated for the task of image set based face and object recognition on YouTube Celebrities, Honda/UCSD, CMU Mobo and ETH-80 (object) dataset, respectively. Experimental results and comparisons with state-of-the-art methods show that our technique achieves the best performance on all these datasets.

Novel Local Surface Representation 3D-Vor [PDF-Pattern Recognition 2015]

In this project we tackled the problem of feature matching and range image registration. Our approach is based on a novel set of discriminating three-dimensional (3D) local features, named 3D-Vor (Vorticity). In contrast to conventional local feature representation techniques, which use the vector field (i.e. surface normals) to just construct their local reference frames, the proposed feature representation exploits the vorticity of the vector field computed at each point of the local surface to capture the distinctive characteristics at each point of the underlying 3D surface. The 3D-Vor descriptors of two range images are then matched using a fully automatic feature matching algorithm which identifies correspondences between the two range images. Correspondences are verified in a local validation step of the proposed algorithm and used for the pairwise registration of the range images. Quantitative results on low resolution Kinect 3D data (Washington RGB-D dataset) show that our proposed automatic registration algorithm is accurate and computationally efficient. The performance evaluation of the proposed descriptor was also carried out on the challenging low resolution Washington RGB-D (Kinect) object dataset, for the tasks of automatic range image registration. Reported experimental results show that the proposed local surface descriptor is robust to resolution, noise and more accurate than state-of-the-art techniques. It achieves 90% registration accuracy compared to 50%, 69.2% and 52% for spin image, 3D SURF and SISI/LD-SIFT descriptors, respectively.

Efficient Depth Segmentation Using Low Resolution Images [PDF-ICIEA2015]

Object segmentation is a fundamental research topic in computer vision. While, only the color information for object segmentation has been the main focus of research, with the availability of low cost color plus range sensors, depth segmentation is now attracting significant attention. This paper presents a novel algorithm for depth segmentation. The proposed technique exploits the divergence of the 2D vector field to segment three-dimensional (3D) object in the depth maps. For a given depth image acquired using a low resolution Kinect sensor, a 2D vector field is computed first at each point of the range image. The depth map is then converted to the div map by computing the 2D vector field’s divergence. The latter maps the vector field to a scalar field. The variation of divergence values over the surface contour of the 3D object helps to extract its boundaries. Finally, the depth segmentation is accomplished by applying a threshold to the div map to segment 3D object from the background. In addition to removing the background, the proposed technique also segments the object from the surface on which the object is positioned. The proposed technique was tested on low resolution Washington RGB-D (Kinect) object dataset. Preliminary experimental results suggest that the proposed algorithm achieves better depth segmentation compared to state-of-the art graph-based depth segmentation. The proposed technique also outperforms the latter by achieving 40% higher computational efficiency.

Novel Local Surface Feature 3D-Div [PDF-ICIP2013]

In this project we proposed a novel local surface descriptor, called 3D-Div. The proposed descriptor is based on the concept of 3D vector field's divergence. To generate a 3D-Div descriptor of a 3D surface, a normalized 3D vector field is computed at each point in the patch and referenced with Local Reference Frame (LRF) vectors. The 3D-Div descriptors are finally generated as the divergence of the reoriented 3D vector field. We tested our proposed descriptor on the low resolution (Kinect) object dataset.

Automatic Object Detection [PDF] [MATLAB Code]

In this work we presented a fully automatic approach to object detection based on an objectness measure. The proposed automatic object detection approach quantifies the likelihood for an image window to encompass objects in the image. It can discriminate between multiple objects in a scene, with individual windows capturing each detected object. Most importantly, the proposed approach does not require any manual input.

Knee Articular Cartilage Quantification [PDF]

In this project we proposed a semi-automatic approach for the analysis, quantification and visualization of knee articular cartilage. Magnetic Resonance Images (MRIs) of the knee were used in this study. Cartilage quantification was carried out by registering different MRIs of the same knee. Finally, a tool for cartilage visualization was also developed. The visualization helped a lot in characterizing the condition of the cartilage in the knee.