Saltar navegación

Activa JavaScript para disfrutar de los vídeos de la Mediateca.

Recognizing images - Contenido educativo

Ajuste de pantalla

El ajuste de pantalla se aprecia al ver el vídeo en pantalla completa. Elige la presentación que más te guste:

Subido el 5 de agosto de 2025 por David G.

19 visualizaciones

Más información Transcripción

Descargar la transcripción

People perceive the world through our senses, but how do machines perceive the world? 00:00:00
Computers use different types of sensors, such as microphones, cameras, radars, or GPS receivers, among others, 00:00:05
to receive information from the environment around them and build a representation of their surroundings. 00:00:13
But computers only know how to work with numbers, so all the information they receive from their sensors must be stored as a set of numbers. 00:00:20
For example, a black and white image is encoded as a matrix of numbers, where each value indicates the brightness of each pixel. 00:00:27
If the image is in color, three numbers are stored for each pixel, representing the brightness of the red, green, and blue components. 00:00:36
Sounds are also encoded as a series of numbers, which indicate the waveform values at different moments, taking hundreds or thousands of samples every second. 00:00:44
Does the fact that a machine can receive information from the world 00:00:53
already make it an artificial intelligence system? 00:00:56
Well no, for us to consider it as such, 00:01:00
it needs to be capable of extracting meaning from that information. 00:01:02
Let's think about a supermarket door that opens when a sensor detects movement. 00:01:06
The system is too simple to be able to perceive who or what is entering 00:01:13
and make decisions based on this meaning. 00:01:16
And thanks to this limitation we can enjoy the wonderful videos 00:01:22
of wild animals walking through supermarket aisles, as Churisky and Garner joke in their 00:01:25
chapter on artificial intelligence literacy in this magnificent work. But how do computers 00:01:31
extract meaning from a set of numbers that represents an image, for example? This transformation 00:01:38
from signal to meaning occurs in progressive stages through a process called feature extraction. 00:01:45
On screen we have an image of a number for written by a person that the computer has 00:01:54
already encoded into a matrix of numbers from the information from its camera. But how could it know 00:01:58
that it's a 4 and not a 1 or a 7? By searching for specific combinations of values that represent 00:02:03
light and dark pixels in small areas of the image, in this case 3 by 3 pixels, the location can be 00:02:10
detected and the orientation of different edges in the image. Thus, the result of applying a filter 00:02:16
to detect left edges is shown in the image on the right, where the areas detected as left edges 00:02:22
appear marked in red. In blue the opposite areas are shown, that is, in this case the right edges. 00:02:26
Let's now apply a filter to detect top edges. See? Well, through this staged process of feature 00:02:42
extraction, in which different types of filters are used and combined, this is how a signal is 00:02:49
transformed into meaning. With sound something very similar is done, for example for voice 00:02:54
recognition, since each vowel and each consonant can be associated with different patterns of a 00:02:59
spectrogram, which is a visual representation that allows identifying the different variations 00:03:04
in frequency and intensity of sound. But there are artificial intelligence systems that are not 00:03:09
only capable of translating audio into text, but also seem to understand these texts. But how can 00:03:15
this be? How is this possible? Well, that's precisely what we're going to see in the next video. 00:03:21
Idioma/s:
en
Materias:
Tecnología
Etiquetas:
Inteligencia Artificial
Niveles educativos:
▼ Mostrar / ocultar niveles
  • Educación Secundaria Obligatoria
    • Ordinaria
      • Primer Ciclo
        • Primer Curso
        • Segundo Curso
      • Segundo Ciclo
        • Tercer Curso
        • Cuarto Curso
        • Diversificacion Curricular 1
        • Diversificacion Curricular 2
    • Compensatoria
Autor/es:
Programamos
Subido por:
David G.
Licencia:
Reconocimiento - No comercial - Compartir igual
Visualizaciones:
19
Fecha:
5 de agosto de 2025 - 17:39
Visibilidad:
Público
Centro:
IES MARIE CURIE Loeches
Duración:
03′ 30″
Relación de aspecto:
1.78:1
Resolución:
854x480 píxeles
Tamaño:
17.27 MBytes

Del mismo autor…

Ver más del mismo autor

EducaMadrid, Plataforma Educativa de la Comunidad de Madrid

Plataforma Educativa EducaMadrid