Daniel Theisges dos Santos
Student Ambassador

Daniel Theisges dos Santos

Blumenau, SC, Brasil

Activity Feed

Medium 1618498 813216372038108 986849409 n

Daniel T. created project HandWritten

Medium 89490a0b d399 4237 a299 d099e6e8d56d

HandWritten

Recognition of offline handwritten text is a useful technique that can be applied to different tasks, such as digitalization of historical documents. However, the unconstrained handwritten text recognition is still considered a very challenging problem. The model presented is composed by an hybrid of convolutional and recurrent neural networks that recognize handwritten text using the image pixels as input features based on deep learning techniques. To train the model a Connectionist Temporal Classification layer was used, wich employs a cost function to align the sequence of label characters to the input sequence. A prototype of this model is implemented and trained using the IAM handwritten text database. The results obtained were satisfactory and show that the model is a valid choice for recognition of off-line handwritten text, beeing robust enough to be able to classify a pattern with so many variability such as handwritten text.

Medium 1618498 813216372038108 986849409 n

Daniel T. created project EMPLOYEE VOLUNTARY TURNOVER

Medium f2a7624a dc40 4ed2 8a9e 1c9d2cf3c186

EMPLOYEE VOLUNTARY TURNOVER

Employee attrition is a critical concern in organizations. All the time and effort spent by many people was, in the end, invested in something that should have lasted at least twice as much. Besides, all that internal knowledge is now out there for competitors to feed from. The cost of an employee leaving can get pretty big.

Data-driven techniques which are based on statistical learning methods exhibit more accurate prediction on employee attrition, as by nature they mathematically model the correlation between factors and attrition outcome and maximize the probability of predicting the correct group of people with a properly trained machine learning model.

1618498 813216372038108 986849409 n

Daniel T. added photos to project BR - Obstacle Detection

Medium c71f199b 6568 4c1a a973 351b04d39762

BR - Obstacle Detection

Implementation of algorithm that performs a detection and classification of Obstacles that exist without means of automation, in real time. Among the Possible obstacles, the initial objective is a classification between automotive vehicles and pedestrians. Knowledge of artificial intelligence and Computational vision will be known, but the specific techniques are determined without results Project development, as it will depend on the student's learning.

Medium 1618498 813216372038108 986849409 n

Daniel T. created project BR - Obstacle Detection

Medium c71f199b 6568 4c1a a973 351b04d39762

BR - Obstacle Detection

Implementation of algorithm that performs a detection and classification of Obstacles that exist without means of automation, in real time. Among the Possible obstacles, the initial objective is a classification between automotive vehicles and pedestrians. Knowledge of artificial intelligence and Computational vision will be known, but the specific techniques are determined without results Project development, as it will depend on the student's learning.

1618498 813216372038108 986849409 n

Daniel T. added photos to project BR-TRAFFIC SIGNS

Medium 1e98d8f2 625b 473d abdc ce9b1a732d8e

BR-TRAFFIC SIGNS

The security in road traffic has become a concern for the society, which motivating the development of Advanced Driver Assistance Systems (ADAS). An example of ADAS is the detection system for traffic signs, which aims to extract traffic information through computer vision te- chniques. In this work it was developed a system capable of detecting Brazilian traffic signs, using for this a new algorithm to filter objects. Firstly, the algorithm extracts objects based on color, applied through a threshold on the space Y’CbCr. After, the post-processing step, a neural network was used with the Fourier descriptors to isolate objects with typical shapes of the Brazilian traffic signs.

1618498 813216372038108 986849409 n

Daniel T. added photos to project E-MOTIV

Medium d8bd313c 55c1 4af9 af8b 9f7785ffb1ba

E-MOTIV

This work presents the development of a prototype for the recognition of universal facial expressions. This technic provides an alternative way of gathering data from the user, being able for usage as an input way for information systems. For faces detection and extraction of their characteristics technics of Computer Vision and Digital Image Processing are employed, implemented by the dlib library with Intel RealSense. The classification into facial expressions is performed by an Artificial Neural Network, of the multilayer perceptron kind.

Medium 1618498 813216372038108 986849409 n

Daniel T. created project E-MOTIV

Medium d8bd313c 55c1 4af9 af8b 9f7785ffb1ba

E-MOTIV

This work presents the development of a prototype for the recognition of universal facial expressions. This technic provides an alternative way of gathering data from the user, being able for usage as an input way for information systems. For faces detection and extraction of their characteristics technics of Computer Vision and Digital Image Processing are employed, implemented by the dlib library with Intel RealSense. The classification into facial expressions is performed by an Artificial Neural Network, of the multilayer perceptron kind.

Medium 1618498 813216372038108 986849409 n

Daniel T. created project BR-TRAFFIC SIGNS

Medium 1e98d8f2 625b 473d abdc ce9b1a732d8e

BR-TRAFFIC SIGNS

The security in road traffic has become a concern for the society, which motivating the development of Advanced Driver Assistance Systems (ADAS). An example of ADAS is the detection system for traffic signs, which aims to extract traffic information through computer vision te- chniques. In this work it was developed a system capable of detecting Brazilian traffic signs, using for this a new algorithm to filter objects. Firstly, the algorithm extracts objects based on color, applied through a threshold on the space Y’CbCr. After, the post-processing step, a neural network was used with the Fourier descriptors to isolate objects with typical shapes of the Brazilian traffic signs.

Medium 1618498 813216372038108 986849409 n

Daniel T. updated status

Medium 1618498 813216372038108 986849409 n

Daniel Theisges dos Santos

I'm working on some fronts right now. Especially with prototype and simulation of connected vehicle systems. I worked in my master's degree with computer vision and embedded systems applied to automated vehicles, especially ADAS. I intend to follow my studies in these approaches with machine learning.

About

Featured Projects

See All

Golden bfff1346 49d7 4ee1 b07c ffde7c78d65b
  • Members 388

DeepLearning

Practical Deep Learning and Machine learning Projects

Bigger andrecarlucci
Black Belt
  • Projects 3
  • Followers 39

Andre Carlucci

Condomínio Centro de Tecnologia Ilhasoft - SC-401, 1 - Saco Grande, Florianópolis - SC, Brazil

Bigger photo
  • Projects 0
  • Followers 3

Tarcisio Nunes

Brusque, Santa Catarina, Brusque - State of Santa Catarina, Brazil

Bigger nader
Innovator
  • Projects 4
  • Followers 179

nader rahman

Z.I. Chotrana II B.P. 160، Pôle Technologique El Ghazela، Ariana 2088, Tunisia

Thumb 07ea97bd 6993 40ea a33a d69ca636c6f4
  • Collaborators 2
  • Followers 78

Follow

Smart City

Thumb nader nader rahman

Created: 05/29/2017

Model of a smart city with electrical components (IOT) accompanied by a mobile application (Android)

Medium real sense
Featured
  • Followers 1970

Intel RealSense™

Natural interaction, immersive, collaboration, gaming and learning, 3D scanning. Integrate tracki...

Medium android
Featured
  • Followers 2012

Android

Intel is inside more and more Android devices, and we have tools and resources to make your app d...

Medium big data
Featured
  • Followers 2081

Modern Code

Drive faster breakthroughs through faster code: Get more results on your hardware today and carry...

Medium networking
Featured
  • Followers 1892

Networking

Software-Defined Networking (SDN) and Network Functions Virtualization (NFV) are transforming the...

Medium achievement unlocked logo
Featured
  • Followers 1820

Game Development

Upgrade your skills as a game developer, share your game projects, and connect with other develop...

Medium vr large 575x441
Featured
  • Followers 1553

Virtual Reality

VR, AR, mixed reality...you'll find projects based on all these new platforms here. Share your own!

Bigger 0 w527swwe4ry9d xybfmfpow6bzjih5vdfem 8coem9m2hirgbfm 0bwo410ihiquqowgtf4b5kytk6bmrfsztcvr5kygko lrfsz swl5kstkbbef74fiivuqj0lnqsr yzh
  • Projects 0
  • Followers 0

Sumit Parvat

H-1100, Awas vikas -1, Kalyanpur, Kanpur, Uttar Pradesh 208017, India

Bigger 0 6vlxqfrjufyk oerbjkwoibjge0pczsgbyahjchvc3u1cyfxivguoc uukzicsug9yaiux 9kis abvtn0kyigrekislabd7n0k1wd eki0 avzyexakswrj3cjnort7aafm
  • Projects 0
  • Followers 0

Aakash Shukla

I am a third year engineering student who loves developing apps and learn new things.

Bhopal, Madhya Pradesh, India

Bigger 11428794 952011164843735 5849042047633955022 n
  • Projects 0
  • Followers 1

CLIFF ERNEST WACHIURI

Fourth year student. Passionate about engineering and how Machine Learning is solving the world's problems.

United Arab Emirates

Bigger 18485522 1446828075437498 4799553862565578279 n
  • Projects 0
  • Followers 0

Ranjeet Saw

I am mad learning about Robotic and 3D Game Robotic game development

Bigger 20171203 130526
  • Projects 0
  • Followers 0

Vibha Rao

Hi! I am Vibha, and I am pursuing my Masters in Computer Science and my area of intrests include neurosciences and artificial intelligence.

Bigger imageedit 2 5954884275
  • Projects 0
  • Followers 0

Haider Ali

I am Haider Ali from Pakistan, Graduated in BE Electronics Engineering from Iqra University Karachi. I am working in Ministry of Energy, Govt. of Pakistan. My research area is in Control Systems, PLC, SCADA, Micro-Controller, Electronics and Communication.

Islamabad, Pakistan

Bigger profile pic
  • Projects 1
  • Followers 2

Bishaw Shrestha

A crazy techno guy enjoying the every little moment , with every little thing, by profession a freelancer and data analyst, as per the interest machine learning, VR/AR.

Kathmandu 44600, Nepal

Bigger robotis op2 advanced humanoid robot us
  • Projects 0
  • Followers 0

Muhammad Qadir

Love to solve real world problems with technlogy

Lahore, Pakistan

Bigger 0 plxkfu1 9d bohynqzjzbsc notmscopbij1n o59gc0smpk 841v8i6cyap4gkp9z4n68c6xbc07ptz6vv0rbg5pbcx7pc0pvvt5uol6s1n7x1npy5pi9fc2y
  • Projects 0
  • Followers 0

Margaret Zhang

Undergraduate in Hunan University, Major in Industry Design, Keen on Artificial Intelligence and Interaction Design

Chengdu, Sichuan, China

See More