Gianluca Francini

Statistical modelling of outliers for fast visual search

The matching of keypoints present in two images is an uncertain process in which many matches may be incorrect. The statistical properties of the log distance ratio for pairs of incorrect matches are distinctly different from the properties of that for correct matches. Based on a statistical model, we propose a goodness-of-fit test in order to establish whether two images contain views of the same object. This technique can be used as a fast geometric consistency check for visual search.

Selection of local features for visual search

In a compact descriptor for visual search only a limited number of local features may be included. The estimated probability for correct match between keypoints provides a good criterion for selection of a subset.

DynamicTV: a culture-aware recommender

A geographically homogeneous group of citizens shares much common knowledge, characteristics of their culture and history. This knowledge is captured for the use in an item-based recommender system that uses textual information, by introducing bias corpora: newspaper articles that represent the shared knowledge. We present a technique for incorporating and quickly replacing bias corpora in a case study of recommendation of TV contents on our IPTV platform. With this recommender, users watched more items and expressed satisfaction with the service.

Automatic license plate recognition with convolutional neural networks trained on synthetic data

We present an Automatic License Plate Recognition system designed around Convolutional Neural Networks (CNNs) and trained over synthetic plate images. We first design CNNs suitable for plate and character detection, sharing a common architecture and training procedure. Then, we generate synthetic images that account for the varying illumination and pose conditions encountered with real plate images and we use exclusively such synthetic images to train our CNNs. Experiments with real vehicle images captured in natural light with commodity imaging systems show precision and recall in excess of 93% despite our networks are trained exclusively on synthetic images.

Deep Classifiers-Based License Plate Detection, Localization and Recognition on GPU-Powered Mobile Platform

The realization of a deep neural architecture on a mobile platform is challenging, but can open up a number of possibilities for visual analysis applications. A neural network can be realized on a mobile platform by exploiting the computational power of the embedded GPU and simplifying the flow of a neural architecture trained on the desktop workstation or a GPU server. This paper presents an embedded platform-based Italian license plate detection and recognition system using deep neural classifiers. In this work, trained parameters of a highly precise automatic license plate recognition (ALPR) system are imported and used to replicate the same neural classifiers on a Nvidia Shield K1 tablet. A CUDA-based framework is used to realize these neural networks. The flow of the trained architecture is simplified to perform the license plate recognition in real-time. Results show that the tasks of plate and character detection and localization can be performed in real-time on a mobile platform by simplifying the flow of the trained architecture. However, the accuracy of the simplified architecture would be decreased accordingly.

Gabor filter based image representation for object classification

Data representation plays an important role in a classifiers accuracy. A given dataset may lead to better results by simply applying a change of basis while keeping the original number of parameters. In this paper, Gabor Filter based image representation has been exploited for object classification. First, Gabor filter based convolution is computed for features extraction, then down-sampling is performed and features are normalized to zero mean and unit variance. This image representation having discriminative visual patterns is used for training of object classifier in Matlab Neural Toolbox. Performance of this proposed image representation is examined on two real world image datasets CIFAR and MNIST and results show that data representation using Gabor can provide good classification without increasing the number of trainable parameters. Finally, this approach is compared to different configurations of Convolutional Neural Network having trainable parameters to verify the validity of proposed image representation.

Fine-grained vehicle classificationusing deep residual networks with multiscale attention windows

Fine-grained vehicle classiflcation is a challenging task due to the subtle differences between vehicle classes. Several successful approaches to fine-grained image classification rely on part-based models, where the image is classified according to discriminative object parts. Such approaches require however that parts in the training images be manually annotated, a laborintensive process. We propose a convolutional architecture realizing a transform network capable of discovering the most discriminative parts of a vehicle at multiple scales. We experimentally show that our architecture outperforms a baseline reference if trained on class labels only, and performs closely to a reference based on a part-model if trained on loose vehicle localization bounding boxes.

GPU-only unified ConvMM layer for neural classifiers

Convolution is most computationally intensive task of Convolutional Neural Network(CNN). It demands both computational power and memory storage of processing unit. There are different approaches to compute the solution of convolution. In this paper, matrix multiplication based convolution(ConvMM) approach is implemented and accelerated using concurrent resources of Graphics Processing Unit(GPU). CUDA computing language is used to implement this layer. Performance of this GPU-only convolutional layer is compared with its heterogeneous version. Further, flow of this GPU-only convolutional layer is optimized using Unified memory by eliminating overhead caused by extra memory transfers.

Efficient Complex High-Precision Computations on GPUs without Precision Loss

General-purpose computing on graphics processing units is the utilization of a graphics processing unit (GPU) to perform computation in applications traditionally handled by the central processing ...

Loop detection in robotic navigation using MPEG CDVS

The choice for image descriptor in a visual navigation system is not straightforward. Descriptors must be distinctive enough to allow for correct localization while still offering low matching complexity and short descriptor size for real-time applications. MPEG Compact Descriptor for Visual Search is a low complexity image descriptor that offers several levels of compromises between descriptor distinctiveness and size. In this work we describe how these trade-offs can be used for efficient loop-detection in a typical indoor environment.