BrainMap

Ioan Catalin Dragoi

- UNIVERSITATEA "VALAHIA" TARGOVISTE

Teaching staff

Web of Science ResearcherID: IQR-5653-2023

Curriculum Vitae (27/02/2025)

Expertise & keywords

Contributions to REversible data hiding in the Encrypted Domain Call name: P 1 - SP 1.1 - Proiecte de cercetare Postdoctorală
PN-III-P1-1.1-PD-2019-1165 2020 - 2022

Role in this project:

Coordinating institution: UNIVERSITATEA "VALAHIA" TARGOVISTE

Project partners: UNIVERSITATEA "VALAHIA" TARGOVISTE (RO)

Affiliation: UNIVERSITATEA "VALAHIA" TARGOVISTE (RO)

Project website: https://creed.valahia.ro/

Abstract:

Reversible data hiding/watermarking (RDH) inserts hidden data into a host signal. This process must be performed in an imperceptible manner that allows for the exact recovery of both the host and the hidden data. Specialized RDH approaches were developed based on the nature of the host file (image, audio or video and more recently plaintext or encrypted).

Recently, the increased interest in Cloud computing platforms and privacy preserving applications has fueled the development of new signal processing algorithms for the encrypted domain. Such an approach, data hiding in the encrypted domain has received renewed interest from the signal processing research community. Reversible data hiding schemes in the encrypted domain (RDH-ED) aim to insert additional information into an encrypted host file without revealing its plaintext content and to exactly recover the original host by extracting the hidden data. Current RDH-ED schemes can be classified into two distinct categories, namely the ones based on vacating room before encryption (VRBE) and those based on vacating room after encryption (VRAE).

The main objectives of the CREED project are to:

- further improve existing VRAE based RDH-ED and develop new VRAE approaches;

- develop a VRAE inspired VRBE RDH-ED scheme that maintains the good performance of VRBE and the standard decryption of VRAE (and other new VRBE approaches);

- develop a generalized RDH-ED framework for multiple file types.

Reversible Data Hiding Based Image Lossless Compression Call name: P 2 - SP 2.1 - Proiect experimental - demonstrativ
PN-III-P2-2.1-PED-2019-2464 2020 - 2022

Role in this project:

Coordinating institution: UNIVERSITATEA "VALAHIA" TARGOVISTE

Project partners: UNIVERSITATEA "VALAHIA" TARGOVISTE (RO)

Affiliation: UNIVERSITATEA "VALAHIA" TARGOVISTE (RO)

Project website: https://rdhc.valahia.ro/

Abstract:

The project aims at developing a new type of software products for lossless image compression where the size of the compressed file is comparable with the one provided by standard lossless compression products and, besides, the content of the compressed image remains visible and completely intelligible. Since the content is visible, the decompression is necessary only when the exact recovery of the original image is required. The idea of such compressors appeared in the framework of the exploratory research project PN-III-P4-IDPCE-2016-0339, when we investigated the improvement of lossless compression by using high capacity reversible data hiding (RDH) algorithms. The basic principle of the proposed RDH-compressors is to reduce image size (by subsampling or cropping) and to embed into the reduced size version, by RDH, the entire information needed to exactly recover the original image. The concept, RDH-compressors, is new and is still unpublished.

The main objectives of the project are to design, develop and test prototypes for the RDH modules and for the RDH-compressors both for graylevel and color images. Our preliminary high capacity RDH schemes are already the state-of-the-art in data hiding and can provide, for graylevel images, embedding bitrates of more than 3 bits per pixel. Improvement of about 0.1 to 0.3 bpp are expected. Besides lossless compressors, the high capacity RDH schemes can be used in complex metadata embedding applications (e.g. embedding images into images). The preliminary RDH-compression rates are similar with the ones of JPEG-LS. The expected prototypes will outperform the compression rates of JPEG-LS and will be rather similar with the ones of PNG and JPEG 2000, with the advantage of immediate access to image content, without any computation. The interest in RDH-compressors is broad and covers any application where digital images are stored, retrieved, manipulated, received or transmitted.

LOcal prediction Watermarking – Second Generation Call name: P 1 - SP 1.1 - Proiecte de cercetare Postdoctorală
PN-III-P1-1.1-PD-2016-1666 2018 - 2020

Role in this project:

Coordinating institution: UNIVERSITATEA "VALAHIA" TARGOVISTE

Project partners: UNIVERSITATEA "VALAHIA" TARGOVISTE (RO)

Affiliation: UNIVERSITATEA "VALAHIA" TARGOVISTE (RO)

Project website: http://low2g.valahia.ro

Abstract:

Watermarking is the imperceptible embedding of data into digital host signals like image, video, audio, text, etc. Its applications are in copyrighting, authentication and annotation. While classical watermarking introduces permanent distortions, reversible watermarking (RW) not only extracts the embedded data, but also recovers the original host signal/image without any distortion. The most efficient RW schemes for digital images embed data into the prediction error. This makes prediction improvement the major research direction in RW.

The best prediction scheme for RW is our local prediction approach (published in IEEE Transactions on Image Processing, 2014) that computes, for each pixel, its own least mean square predictor in a local block. The same predictor is recovered at detection without any additional information.

The main objectives of the LOW-2G projects are to:

1) Develop novel prediction schemes. Instead of fixed prediction parameters as considered in the original local prediction scheme, we shall investigate the use of the adaptive parameters for the learning block sizing, the adaptive changing of the size and/or shape of the prediction context and different optimization techniques for local predictor computation (least mean squares (LMS), iteratively reweighted least squares (IRLS), etc.).

2) Develop a new generation of RW schemes based on local prediction and investigate their applications. The novel prediction schemes will be used to develop a new generation of RW schemes of lower distortion than the state-of-the-art ones. Gains of 2-4 dB are expected. Fast algorithms and fast implementations of the proposed schemes will be also investigated. New applications taking advantage of the lower distortion introduced by the new LOW-2G schemes will be developed in the framework of the project.

reverSible Watermarking: Advanced Techniques Call name: P 4 - Proiecte de Cercetare Exploratorie
PN-III-P4-ID-PCE-2016-0339 2017 - 2019

Role in this project:

Coordinating institution: UNIVERSITATEA "VALAHIA" TARGOVISTE

Project partners: UNIVERSITATEA "VALAHIA" TARGOVISTE (RO)

Affiliation: UNIVERSITATEA "VALAHIA" TARGOVISTE (RO)

Project website: http://www.swat.valahia.ro

Abstract:

Watermarking is a modern communication paradigm that creates a covert data channel into digital host signals (image, video, audio, etc.). Its applications are in copyrighting, data authentication, metadata embedding. Reversible watermarking (RW) ensures the exact recovery of both the embedded data and the original host. While much research has been devoted to RW schemes of medium embedding bit-rates (
The project SWAT aims to develop high embedding bit-rate and low distortion RW schemes. Beside the practical interest for the resulted algorithms, our research is of theoretical interest for the watermarking and generally, signal/image processing community. The main objectives of the SWAT projects are to: 1) Develop novel RW algorithms of high embedding bit-rate; 2) Investigate and develop high embedding bit-rate RW applications; 3) Investigate lossless compression improvement by using RW.

The proposed algorithms will outperform the state-of-the-art ones with about 20-30%. For natural images we expect > 3 bpp. We also expect at the same bit-rates, gains in quality of 3-6 dB. Complex applications will be investigated for graylevel as well as for other types of images (color, video sequences, multispectral, 3D). While so far, RW has taken advantage of the research in lossless compression, we believe that now it is time that RW contributes to lossless compression as well. For instance, the new predictors developed for RW could be tested in compression too.

Methods of prediction of infantile hemangiomas evolution, aimed at preventing desfigurating complications by multiple intervention procedures Call name: Joint Applied Research Projects - PCCA 2013 - call
PN-II-PT-PCCA-2013-4-0201 2014 - 2017

Role in this project:

Coordinating institution: UNIV.DE MEDICINA SI FARMACIE - CAROL DAVILA

Project partners: UNIV.DE MEDICINA SI FARMACIE - CAROL DAVILA (RO); UNIVERSITATEA POLITEHNICA DIN BUCURESTI (RO); UNIVERSITATEA "VALAHIA" TARGOVISTE (RO); SANAFORT SRL (RO)

Affiliation: UNIVERSITATEA "VALAHIA" TARGOVISTE (RO)

Project website: http://imag.pub.ro/hemacad/

Abstract:

Infantile Hemangiomas (IH) are tumors of vascular origin that are present at birth or develop a few weeks after. The differential diagnosis from vascular malformations is difficult to establish. IH that affect the cephalic and cervical region (the most frequent), the genital area or the extremities, due to the location, dimensions and fast evolution, can determine important functional and esthetic sequels, debilitating for the patient. To avoid these unfortunate consequences it is necessary to establish the exact appropriate moment to begin the treatment and decide which is the most adequate therapeutic procedure.

Until now, at international level there is no standard method of diagnosis of infantile hemangiomas nor any mean of predicting their progress from the clinical point of view and possible complications that may appear. Treatments currently used rely only on subjective observation, instinct and experience of the treating physician, supported by technical and pharmacological development in medicine.

The proposed project intends, based on clinical data collected by serial clinical observations correlated with imaging data, to develop a treatment algorithm to accurately predict the best final results, from esthetical and functional point of view, for a certain type of lesion.

In order to achieve this goal, we will use and/or develop modern methods to process medical images and intelligent algorithms to help the diagnosis (CAD). The software will incorporate advanced methods for accurate measurement of specific IH lesions, will integrate medical information resulting from clinical observations and integrate statistical methods and / or nature-inspired computational methods (e.g. nonlinear dynamics, cellular neural networks, artificial neural networks) to correlate this information with that obtained from the processing of images. Based on these correlations we will establish a prediction mechanism of the evolution of hemangioma. This will help determine the best method of therapeutic intervention to minimize further complications.

The scientific and technological impact of the project resides in the development of these innovative methods. Their implementation will result in a medical device type of product that will obviously help to increase the competitiveness of the Romanian economy, given that the existence of such a product, which aims to really improve the quality of life for children affected by an esthetic and functional disfiguring pathology, is a must.

The product implies real health benefits for both patients and the health system receiving a minimization of costs per patient in this condition. By decreasing the number of procedures and defining a single therapeutic strategy for treating a patient, amounts can be saved and consequently allocated for the benefit of other needs. Moreover, if the aesthetic and functional result is maximized, we save the resources allocated for the patient’s reintegration into society, which is more costly if the degree of failure is higher. Decreasing the disease follow up period, speeding the diagnosis, diminishing the hospitalization time, a faster social integration of the patients are only a few benefits that such a product would bring, not only for the patients, but also for the national and European medical system.

The consortium consisting of “Carol Davila” University of Medicine and Pharmacy Bucharest (project coordinator), University Politehnica from Bucuresti (P1), University Valahia of Târgoviște (P2) and Medical Technologies & Research company (P3) formed a close-knit team to successfully implement the project.

Intelligent system for management, monitoring and maintenance of pavements and roads using modern imaging techniques-PAV3M Call name: Joint Applied Research Projects - PCCA 2013 - call
PN-II-PT-PCCA-2013-4-1762 2014 - 2017

Role in this project: Key expert

Coordinating institution: UNIVERSITATEA BABES BOLYAI

Project partners: UNIVERSITATEA BABES BOLYAI (RO); CENTRUL IT PENTRU STIINTA SI TEHNOLOGIE S.R.L. (RO); CENTRUL DE COMPETENTA IN ELECTROSTATICA SI ELECTROTEHNOLOGII S.R.L. (RO); UNIVERSITATEA "VALAHIA" TARGOVISTE (RO); UNIVERSITATEA "DUNAREA DE JOS" (RO); UNIVERSITATEA TEHNICA DIN CLUJ - NAPOCA (RO)

Affiliation: UNIVERSITATEA "VALAHIA" TARGOVISTE (RO)

Project website: https://econ.ubbcluj.ro/PAV3M, https://www.facebook.com/pages/PAV3M/757415914312096

Abstract:

The primary objective of PAV3M is to develop a holistic platform which integrates imaging based road pavement inspection technology with a risk management and cost/benefits application software tool to support road management needs of transportation agencies, construction and road rehabilitation companies and local governments. On the technological side we propose an automated, portable visual pavement inspection system for traffic-speed pavement distress monitoring and analysis of road pavements whose high degree of integration, easy mountability and costs will permit its operation on non-specialized vehicles and thus its widespread use. Current approaches for road condition data collection are done by specialized vehicles at substantial costs and long inspection cycles. In some cases, due to limited funding, officials even relay on time-consuming manual labor. Yet the importance for traffic safety of timely identification and rectification of road deformations cannot be overstated.

PAV3M will exploit recent advances in image acquisition hardware (higher resolution sensors, faster and more light sensitive digital cameras, increased data acquisition rates, etc.) and the tremendous increase in processing/computing power of “miniatural” units. The proposed system will consist of an innovative camera system and a full set of additional sensors for positioning, orientation and communication. Within PAV3M we will develop efficient algorithms and methods for automated image and video processing to identify and quantify road pavement surface condition parameters. Coupling this information with prediction of defects and with a cost and risk management application will endow the road owners with a methodology to assess the current status of the pavements and to evaluate the effect of maintenance techniques on the pavement capital.

Economic and risk management aspects (UBB) together with defect evolution prediction will be fully integrated into a web portal offering a service that is part of the SMEs (CITST and CCEE) business strategy for targeting the fast developing Romanian road management sector. Intelligent System development will follow Oguara objectives of Pavement Maintenance and Management Systems (PMMS) linked with management tools and functionality. Our proposal links together PMMS and PMS (Pavement Management Systems) in a web-based multi-tier modular solution, which will be offered as a SaaS (Software as a Service) through a web portal.

Using semantic Web we propose a road history database, which can be used in the risk management module. An expert module assists the decision makers in finding optimum strategies for maintaining pavements and the risk module offers solutions for avoid or mitigate risk factors in a given period of time for the minimum cost. This module will offer alternative strategies to cover the wide range of risks associated with pavements, which was proposed by Paine, based on Unified Facilities Criteria for Pavement Maintenance Management.

Partners involved in the project ensure the complementary synergies in a trans-disciplinary approach, based on their competencies, involving a number of interrelated disciplines. We mention relevant expertise in hardware integration, image processing and pattern recognition area, multimedia databases, business process management, risk management, e-business application, portals and web technologies, Web services.

New methods and investigations protocols for the early diagnosis, efficient screening, prognostic and therapy of non-melanoma skin cancers based on existing and novel micro & nano optical tools Call name: Joint Applied Research Projects - PCCA-2011 call, Type 2
PN-II-PT-PCCA-2011-3.2-1162 2012 - 2016

Role in this project: Key expert

Coordinating institution: UNIVERSITATEA POLITEHNICA DIN BUCURESTI

Project partners: UNIVERSITATEA POLITEHNICA DIN BUCURESTI (RO); SPITALUL CLINIC DE URGENTA (RO); UNIVERSITATEA "VALAHIA" TARGOVISTE (RO); WING COMPUTER GROUP S.R.L. (RO)

Affiliation: UNIVERSITATEA "VALAHIA" TARGOVISTE (RO)

Project website: http://nanolascan.ro

Abstract:

Skin cancer is among the most common forms of cancer in the USA, Australia, and Europe and is increasing in incidence in other parts of the world. The rising incidence of non-melanoma skin cancer, such as basal cell carcinoma (BCC) and squamous cell carcinoma (SCC), makes the investigation of the tumors of this type to represent a subject of maximum importance at this time. The precise visualization and understanding of cellular and sub-cellular structures specific to cancer tumors is essential for establishing a correct diagnostic at a very early stage, as well as for the efficient monitoring of the tumor evolution and of the effects of the administered therapy. We propose to develop and use a commercially unavailable microscopy system, FASNOM, to advance the current understanding on the morphological and autofluorescent nanoscale features found in freshly excised human non-melanoma skin cancer and normal perilesional skin samples. The diagnostic potential of fluorescence imaging and spectroscopy lies in the ability to noninvasively probe alterations in tissue morphology and biochemistry that occur during malignant progression. In this purpose we propose to exploit nanoscale information on the properties of endogenous fluorescent biomolecules present in human skin in order to distinguish between normal, pre-cancerous and cancerous epithelial tissues of different types with high specificity and sensitivity. In the proposed project high importance will be given to identifying nanoscale (

FILE DESCRIPTION	DOCUMENT
List of research grants as project coordinator or partner team leader	Download (41.93 kb) 28/01/2019
Significant R&D projects for enterprises, as project manager
R&D activities in enterprises
Peer-review activity for international programs/projects