Salman Hameed Khan

Automatic Shadow Detection and Removal from a Single Image

We present a framework to automatically detect and remove shadows in real world scenes from a single image. Previous works on shadow detection put a lot of effort in designing shadow variant and invariant hand-crafted features. In contrast, our framework automatically learns the most relevant features in a supervised manner using multiple convolutional deep neural networks (ConvNets). The features are learned at the super-pixel level and along the dominant boundaries in the image. The predicted posteriors based on the learned features are fed to a conditional random field model to generate smooth shadow masks. Using the detected shadow masks, we propose a Bayesian formulation to accurately extract shadow matte and subsequently remove shadows. The Bayesian formulation is based on a novel model which accurately models the shadow generation process in the umbra and penumbra regions. The model parameters are efficiently estimated using an iterative optimization procedure. Our proposed framework consistently performed better than the state-of-the-art on all major shadow databases collected under a variety of conditions.

Automatic Feature Learning for Robust Shadow Detection

We present a practical framework to automatically detect shadows in real world scenes from a single photograph. Previous works on shadow detection put a lot of effort in designing shadow variant and invariant hand-crafted features. In contrast, our framework automatically learns the most relevant features in a supervised manner using multiple convolutional deep neural networks (ConvNets). The 7-layer network architecture of each ConvNet consists of alternating convolution and sub-sampling layers. The proposed framework learns features at the super-pixel level and along the object boundaries. In both cases, features are extracted using a context aware window centered at interest points. The predicted posteriors based on the learned features are fed to a conditional random field model to generate smooth shadow contours. Our proposed framework consistently performed better than the state-of-the-art on all major shadow databases collected under a variety of conditions.

Geometry Driven Semantic Labeling of Indoor Scenes

We present a discriminative graphical model which integrates geometrical information from RGBD images in its unary, pairwise and higher order components. We propose an improved geometry estimation scheme which is robust to erroneous sensor inputs. At the unary level, we combine appearance based beliefs defined on pixels and planes using a hybrid decision fusion scheme. Our proposed location potential gives an improved representation of the planar classes. At the pairwise level, we learn a balanced combination of various boundaries to consider the spatial discontinuity. Finally, we treat planar regions as higher order cliques and use graphcuts to make efficient inference. In our model based formulation, we use structured learning to fine tune the model parameters. We test our approach on two RGBD datasets and demonstrate significant improvements over the state-of-the-art scene labeling techniques.

Cost-Sensitive Learning of Deep Feature Representations From Imbalanced Data

Class imbalance is a common problem in the case of real-world object detection and classification tasks. Data of some classes are abundant, making them an overrepresented majority, and data of other classes are scarce, making them an underrepresented minority. This imbalance makes it challenging for a classifier to appropriately learn the discriminating boundaries of the majority and minority classes. In this paper, we propose a cost-sensitive (CoSen) deep neural network, which can automatically learn robust feature representations for both the majority and minority classes. During training, our learning procedure jointly optimizes the class-dependent costs and the neural network parameters. The proposed approach is applicable to both binary and multiclass problems without any modification. Moreover, as opposed to data-level approaches, we do not alter the original data distribution, which results in a lower computational cost during the training process. We report the results of our experiments on six major image classification data sets and show that the proposed approach significantly outperforms the baseline algorithms. Comparisons with popular data sampling techniques and CoSen classifiers demonstrate the superior performance of our proposed method.

Integrating Geometrical Context for Semantic Labeling of Indoor Scenes using RGBD Images

Inexpensive structured light sensors can capture rich information from indoor scenes, and scene labeling problems provide a compelling opportunity to make use of this information. In this paper we present a novel conditional random field (CRF) model to effectively utilize depth information for semantic labeling of indoor scenes. At the core of the model, we propose a novel and efficient plane detection algorithm which is robust to erroneous depth maps. Our CRF formulation defines local, pairwise and higher order interactions between image pixels. At the local level, we propose a novel scheme to combine energies derived from appearance, depth and geometry-based cues. The proposed local energy also encodes the location of each object class by considering the approximate geometry of a scene. For the pairwise interactions, we learn a boundary measure which defines the spatial discontinuity of object classes across an image. To model higher-order interactions, the proposed energy treats smooth surfaces as cliques and encourages all the pixels on a surface to take the same label. We show that the proposed higher-order energies can be decomposed into pairwise sub-modular energies and efficient inference can be made using the graph-cuts algorithm. We follow a systematic approach which uses structured learning to fine-tune the model parameters. We rigorously test our approach on SUN3D and both versions of the NYU-Depth database. Experimental results show that our work achieves superior performance to state-of-the-art scene labeling techniques.

A Discriminative Representation of Convolutional Features for Indoor Scene Recognition

Indoor scene recognition is a multi-faceted and challenging problem due to the diverse intra-class variations and the confusing inter-class similarities that characterize such scenes. This paper presents a novel approach that exploits rich mid-level convolutional features to categorize indoor scenes. Traditional convolutional features retain the global spatial structure, which is a desirable property for general object recognition. We, however, argue that the structure-preserving property of the convolutional neural network activations is not of substantial help in the presence of large variations in scene layouts, e.g., in indoor scenes. We propose to transform the structured convolutional activations to another highly discriminative feature space. The representation in the transformed space not only incorporates the discriminative aspects of the target data set but also encodes the features in terms of the general object categories that are present in indoor scenes. To this end, we introduce a new large-scale data set of 1300 object categories that are commonly present in indoor scenes. Our proposed approach achieves a significant performance boost over the previous state-of-the-art approaches on five major scene classification data sets.

A Spatial Layout and Scale Invariant Feature Representation for Indoor Scene Classification

Unlike standard object classification, where the image to be classified contains one or multiple instances of the same object, indoor scene classification is quite different since the image consists of multiple distinct objects. Furthermore, these objects can be of varying sizes and are present across numerous spatial locations in different layouts. For automatic indoor scene categorization, large-scale spatial layout deformations and scale variations are therefore two major challenges and the design of rich feature descriptors which are robust to these challenges is still an open problem. This paper introduces a new learnable feature descriptor called “spatial layout and scale invariant convolutional activations” to deal with these challenges. For this purpose, a new convolutional neural network architecture is designed which incorporates a novel “spatially unstructured” layer to introduce robustness against spatial layout deformations. To achieve scale invariance, we present a pyramidal image representation. For feasible training of the proposed network for images of indoor scenes, this paper proposes a methodology, which efficiently adapts a trained network model (on a large-scale data) for our task with only a limited amount of available training data. The efficacy of the proposed approach is demonstrated through extensive experiments on a number of data sets, including MIT-67, Scene-15, Sports-8, Graz-02, and NYU data sets.

Joint Registration and Representation Learning for Unconstrained Face Identification

Recent advances in deep learning have resulted in human-level performances on popular unconstrained face datasets including Labeled Faces in the Wild and YouTube Faces. To further advance research, IJB-A benchmark was recently introduced with more challenges especially in the form of extreme head poses. Registration of such faces is quite demanding and often requires laborious procedures like facial landmark localization. In this paper, we propose a Convolutional Neural Networks based data-driven approach which learns to simultaneously register and represent faces. We validate the proposed scheme on template based unconstrained face identification. Here, a template contains multiple media in the form of images and video frames. Unlike existing methods which synthesize all template media information at feature level, we propose to keep the template media intact. Instead, we represent gallery templates by their trained one-vs-rest discriminative models and then employ a Bayesian strategy which optimally fuses decisions of all medias in a query template. We demonstrate the efficacy of the proposed scheme on IJB-A, YouTube Celebrities and COX datasets where our approach achieves significant relative performance boosts of 3.6%, 21.6% and 12.8% respectively.

Activity monitoring of workers using single wearable inertial sensor

This Activity monitoring of workers in installations such as industries, underground tunnels, sewerage lines, remote field deployments etc. is a daunting task. Due to lack of communication systems and scarce energy resources, these scenarios pose great challenges in developing a monitoring system for workers. The design of activity recognition system for workers, using a single tri-axial accelerometer is presented in this paper. Time, frequency and spatial domain features were extracted using a naturalistic dataset and were used to analyze the performance of various classifiers. FFT energy, entropy and correlation between axes showed good results in classification of 9 different activities. The various classification algorithms were tested using Weka classification tool and we have achieved up to 93.9% successful classification results using Random Forest algorithm.

Multi-Factor Authentication on Cloud

Due to the recent security infringement incidents of single factor authentication services, there is an inclination towards the use of multi-factor authentication (MFA) mechanisms. These MFA mechanisms should be available to use on modern hand-held computing devices like smart phones due to their big share in computational devices market. Moreover, the high social acceptability and ubiquitous nature has attracted the enterprises to offer their services on modern day hand-held devices. In this regard, the big challenge for these enterprises is to ensure security and privacy of users. To address this issue, we have implemented a verification system that combines human inherence factor (handwritten signature biometrics) with the standard knowledge factor (user specific passwords) to achieve a high level of security. The major computational load of the aforementioned task is shifted on a cloud based application server so that a platform-independent user verification service with ubiquitous access becomes possible. Custom applications are built for both the iOS and Android based devices which are linked with the cloud based two factor authentication (TFA) server. The system is tested on-the-run by a diverse group of users and 98.4% signature verification accuracy is achieved.