Rajeev Ranjan

Learn More
We present a face detection algorithm based on De-formable Part Models and deep pyramidal features. The proposed method called DP2MFD is able to detect faces of various sizes and poses in unconstrained conditions. It reduces the gap in training and testing of DPM on deep features by adding a normalization layer to the deep convolu-tional neural network(More)
We present an algorithm for simultaneous face detection, landmarks localization, pose estimation and gender recognition using deep convolutional neural networks (CNN). The proposed method called, Hyperface, fuses the intermediate layers of a deep CNN using a separate CNN and trains multi-task loss on the fused features. It exploits the syn-ergy among the(More)
We present an algorithm for extracting key-point descrip-tors using deep convolutional neural networks (CNN). Unlike many existing deep CNNs, our model computes local features around a given point in an image. We also present a face alignment algorithm based on regression using these local descriptors. The proposed method called Local Deep Descriptor(More)
We propose an approach for age estimation from uncon-strained images based on deep convolutional neural networks (DCNN). Our method consists of four steps: face detection, face alignment, DCNN-based feature extraction and neural network regression for age estimation. The proposed approach exploits two insights: (1) Features obtained from DCNN trained for(More)
Over the last four years, methods based on Deep Convolutional Neural Networks (DCNNs) have shown impressive performance improvements for object detection and recognition problems. This has been made possible due to the availability of large annotated datasets, a better understanding of the non-linear mapping between input images and class labels as well as(More)
It has now become an important issue to evaluate the performance of technical institutions to develop better research and enrich the existing teaching processes. The results of such performance appraisal would serve as a reference point for decisions to choose a particular institution, hire manpower, and provide financial support for the betterment of(More)
BACKGROUND Mid-gestation fetal cutaneous wounds heal scarlessly and this has been attributed in part to abundant hyaluronan (HA) in the extracellular matrix (ECM) and a unique fibroblast phenotype. We recently reported a novel role for interleukin 10 (IL-10) as a regulator of HA synthesis in the fetal ECM, as well as the ability of the fetal fibroblast to(More)
Over the last four years, methods based on Deep Convolutional Neural Networks (DCNNs) have shown impressive performance improvements for object detection and recognition problems. This has been made possible due to the availability of large annotated datasets, a better understanding of the non-linear mapping between input images and class labels as well as(More)