The visual analysis of peripheral blood samples is an important test in the procedures for the diagnosis of leukemia. Automated systems based on artificial vision methods can speed up this operation and increase the accuracy and homogeneity of the response also in telemedicine applications. Unfortunately, there are not available public image datasets to test and compare such algorithms. In this paper, we propose a new public dataset of blood samples, specifically designed for the evaluation and the comparison of algorithms for segmentation and classification. For each image in the dataset, the classification of the cells is given, as well as a specific set of figures of merits to fairly compare the performances of different algorithms. This initiative aims to offer a new test tool to the image processing and pattern matching communities, direct to stimulating new studies in this important field of research.

We present a privacy preserving protocol for fingerprint-based authentication. We consider a scenario where a client equipped with a fingerprint reader is interested into learning if the acquired fingerprint belongs to the database of authorized entities managed by a server. For security, it is required that the client does not learn anything on the database and the server should not get any information about the requested biometry and the outcome of the matching process. The proposed protocol follows a multi-party computation approach and makes extensive use of homomorphic encryption as underlying cryptographic primitive. To keep the protocol complexity as low as possible, a particular representation of fingerprint images, named Fingercode, is adopted. Although the previous works on privacy-preserving biometric identification focus on selecting the best matching identity in the database, our main solution is a generic identification protocol and it allows to select and report all the enrolled identities whose distance to the user's fingercode is under a given threshold. Variants for simple authentication purposes are provided. Our protocols gain a notable bandwidth saving (about 25-39%) if compared with the best previous work (ICISC'09) and its computational complexity is still low and suitable for practical applications. Moreover, even if such protocols are presented in the context of a fingerprint-based system, they can be generalized to any biometric system that shares the same matching methodology, namely distance computation and thresholding.

The privacy protection of the biometric data is an important research topic, especially in the case of distributed biometric systems. In this scenario, it is very important to guarantee that biometric data cannot be steeled by anyone, and that the biometric clients are unable to gather any information different from the single user verification/identification. In a biométrie system with high level of privacy compliance, also the server that processes the biométrie matching should not learn anything on the database and it should be impossible for the server to exploit the resulting matching values in order to extract any knowledge about the user presence or behavior. Within this conceptual framework, in this paper we propose a novel complete demonstrator based on a distributed biométrie system that is capable to protect the privacy of the individuals by exploiting cryptosystems. The implemented system computes the matching task in the encrypted domain by exploiting homomorphic encryption and using Fingercode templates. The paper describes the design methodology of the demonstrator and the obtained results. The demonstrator has been fully implemented and tested in real applicative conditions. Experimental results show that this method is feasible in the cases where the privacy of the data is more important than the accuracy of the system and the obtained computational time is satisfactory.

Since Synthetic Aperture Radar (SAR) targets are full of coherent speckle noise, the traditional deep learning models are difficult to effectively extract key features of the targets and share high computational complexity. To solve the problem, an effective lightweight Convolutional Neural Network (CNN) model incorporating transfer learning is proposed for better handling SAR targets recognition tasks. In this work, firstly we propose the Atrous-Inception module, which combines both atrous convolution and inception module to obtain rich global receptive fields, while strictly controlling the parameter amount and realizing lightweight network architecture. Secondly, the transfer learning strategy is used to effectively transfer the prior knowledge of the optical, non-optical, hybrid optical and non-optical domains to the SAR target recognition tasks, thereby improving the model’s recognition performance on small sample SAR target datasets. Finally, the model constructed in this paper is verified to be 97.97% on ten types of MSTAR datasets under standard operating conditions, reaching a mainstream target recognition rate. Meanwhile, the method presented in this paper shows strong robustness and generalization performance on a small number of randomly sampled SAR target datasets.