The relationship between face and disease has been discussed from thousands years ago, which leads to the occurrence of facial diagnosis. The objective here is to explore the possibility of identifying diseases from uncontrolled 2D face images by deep learning techniques. In this paper, we propose using deep transfer learning from face recognition to perform the computer-aided facial diagnosis on various diseases. In the experiments, we perform the computer-aided facial diagnosis on single (beta-thalassemia) and multiple diseases (beta-thalassemia, hyperthyroidism, Down syndrome, and leprosy) with a relatively small dataset. The overall top-1 accuracy by deep transfer learning from face recognition can reach over 90% which outperforms the performance of both traditional machine learning methods and clinicians in the experiments. In practical, collecting disease-specific face images is complex, expensive and time consuming, and imposes ethical limitations due to personal data treatment. Therefore, the datasets of facial diagnosis related researches are private and generally small comparing with the ones of other machine learning application areas. The success of deep transfer learning applications in the facial diagnosis with a small dataset could provide a low-cost and noninvasive way for disease screening and detection.

In the last decade, advances and popularity of low-cost RGB-D sensors have enabled us to acquire depth information of objects. Consequently, researchers began to solve face recognition problems by capturing RGB-D face images using these sensors. Until now, it is not easy to acquire the depth of human faces because of limitations imposed by privacy policies, and RGB face images are still more common. Therefore, obtaining the depth map directly from the corresponding RGB image could be helpful to improve the performance of subsequent face processing tasks, such as face recognition. Intelligent creatures can use a large amount of experience to obtain 3D spatial information only from 2D plane scenes. It is machine learning methodology, which is to solve such problems, that can teach computers to generate correct answers by training. To replace the depth sensors by generated pseudo-depth maps, in this article, we propose a pseudo RGB-D face recognition framework and provide data-driven ways to generate the depth maps from 2D face images. Specially we design and implement a generative adversarial network model named “D+GAN” to perform the multiconditional image-to-image translation with face attributes. By this means, we validate the pseudo RGB-D face recognition with experiments on various datasets. With the cooperation of image fusion technologies, especially non-subsampled shearlet transform (NSST), the accuracy of face recognition has been significantly improved.

Object detection and recognition is a key component of autonomous robotic vehicles, as evidenced by the continuous efforts made by the robotic community on areas related to object detection and sensory perception systems. This paper presents a study on multisensor (camera and LIDAR) late fusion strategies for object recognition. In this work, LIDAR data is processed as 3D points and also by means of a 2D representation in the form of depth map (DM), which is obtained by projecting the LIDAR 3D point cloud into a 2D image plane followed by an upsampling strategy which generates a high-resolution 2D range view. A CNN network (Inception V3) is used as classification method on the RGB images, and on the DMs (LIDAR modality). A 3D-network (the PointNet), which directly performs classification on the 3D point clouds, is also considered in the experiments. One of the motivations of this work consists of incorporating the distance to the objects, as measured by the LIDAR, as a relevant cue to improve the classification performance. A new range-based average weighting strategy is proposed, which considers the relationship between the deep-models’ performance and the distance of objects. A classification dataset, based on the KITTI database, is used to evaluate the deep-models, and to support the experimental part. We report extensive results in terms of single modality i.e., using RGB and LIDAR models individually, and late fusion multimodality approaches.

Estimating the amount and center of distortion from lines in the scene has been addressed in the literature by the so-called ``plumb-line'' approach. In this paper we propose a new geometric method to estimate not only the distortion parameters but the entire camera calibration (up to an ``angular'' scale factor) using a minimum of 3 lines. We propose a new framework for the unsupervised simultaneous detection of natural image of lines and camera parameters estimation, enabling a robust calibration from a single image. Comparative experiments with existing automatic approaches for the distortion estimation and with ground truth data are presented.

This paper presents a study on pedestrian classification based on deep learning using data from a monocular camera and a 3D LIDAR sensor, separately and in combination. Early and late multi-modal sensor fusion approaches are revisited and compared in terms of classification performance. The problem of pedestrian classification finds applications in advanced driver assistance system (ADAS) and autonomous driving, and it has regained particular attention recently because, among other reasons, safety involving self-driving vehicles. Convolutional Neural Networks (CNN) is used in this work as classifier in distinct situations: having a single sensor data as input, and by combining data from both sensors in the CNN input layer. Range (distance) and intensity (reflectance) data from LIDAR are considered as separate channels, where data from the LIDAR sensor is feed to the CNN in the form of dense maps, as the result of sensor coordinate transformation and spatial filtering; this allows a direct implementation of the same CNN-based approach on both sensors data. In terms of late-fusion, the outputs from individual CNNs are combined by means of learning and non-learning approaches. Pedestrian classification is evaluated on a `binary classification' dataset created from the KITTI Vision Benchmark Suite, and results are shown for each sensor-modality individually, and for the fusion strategies.