Object recognition

MIT grad student Joy Buolamwini (left) meets author Margot Lee Shetterly at an MIT screening of "Hidden Figures."

Joy Buolamwini wins national contest for her work fighting bias in machine learning

Media Lab graduate student selected from over 7,300 entrants, awarded $50,000 scholarship in contest inspired by the film "Hidden Figures."

January 17, 2017

For each image, the MemNet algorithm creates a heat map identifying its most memorable and forgettable regions.

Deep-learning algorithm predicts photos’ memorability at “near-human” levels

Future versions of an algorithm from the Computer Science and Artificial Intelligence Lab could help with teaching, marketing, and memory improvement.

December 16, 2015

Researchers have found that neuron firing patterns in the inferior temporal (IT) cortex, highlighted here, correlate strongly with success in object-recognition tasks.

How the brain recognizes objects

Neuroscientists find evidence that the brain’s inferotemporal cortex can identify objects.

October 5, 2015

A new soft robotic gripper from MIT can estimate the size and shape of an object accurately enough to identify it from a set of multiple items.

Soft robotic hand can pick up and identify a wide array of objects

Team from Computer Science and Artificial Intelligence Lab develops silicone rubber gripper and advanced object-identification algorithms.

September 30, 2015

The first layers (1 and 2) of a neural network trained to classify scenes seem to be tuned to geometric patterns of increasing complexity, but the higher layers (3 and 4) appear to be picking out particular classes of objects.

Object recognition for free

System designed to label visual scenes according to type turns out to detect particular objects, too.

May 8, 2015

Vision system for household robots

New algorithm could enable household robots to better identify objects in cluttered environments.

January 12, 2015

Vivienne Sze receives DARPA 2014 Young Faculty Award

Award honors work on real-time energy-efficient visual data processing for portable media, which will impact elderly-assistance and advanced driver-assistance systems.

December 23, 2014

A team of MIT neuroscientists has found that some computer programs can identify the objects in these images just as well as the primate brain.

In one aspect of vision, computers catch up to primate brain

Newest computer neural networks can identify visual objects as well as the primate brain.

December 18, 2014

Orienteering for robots

Algorithm for determining orientation of objects could aid robots in navigation, scene understanding.

April 4, 2014

MIT researchers combined fMRI and MEG data to reveal which parts of the brain are active shortly after an image is seen. At around 60 milliseconds, only early visual cortex in the back of the brain was active (image at left). Then, activity spread to brain regions involved in later visual processing until the inferior temporal cortex was activated (image at right). This brain region represents com...

Expanding our view of vision

New brain-scanning technique allows scientists to see when and where the brain processes visual information.

January 26, 2014

Two examples of faces that have been modified from an original photo (center) to look more (right) and less (left) memorable without altering their identity, attractiveness, age, or gender.

Never forget a face

New algorithm uses subtle changes to make a face more memorable without changing a person’s overall appearance.

December 18, 2013

With each of the raw images at left (color), today's state-of-the-art
object-detection algorithms make errors that initially seem baffling — such as mistaking distant clouds for a nearby car. A new
technique enables the visualization of a common mathematical
representation of
images (in black and white), which should help researchers understand why
their
algorithms fail.

Teaching computers to see — by learning to see like computers

By translating images into the language spoken by object-recognition systems, then translating them back, researchers hope to explain the systems’ failures.

September 19, 2013

Aude Oliva, a principal investigator in MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) and an associate professor in the Department of Brain and Cognitive Sciences (BCS)

Oliva explores new ground in computational perception at CSAIL

Neuroscientist looks forward to collaborative studies of visual perception in the brain and its computational applications.

November 8, 2011

New research suggests that some parts of the brain perceive a scene and its mirror image as one and the same, meaning those regions are involved in scene categorization rather than navigation.

Scene perception versus action in the brain

Cognitive neuroscientists shed light on how the brain responds to scenes and their mirror-image reversals.

August 18, 2011

Finding an edge

An algorithm for identifying the boundaries of objects in digital images is 50,000 times more efficient than its predecessor.

May 31, 2011

MIT News | Massachusetts Institute of Technology

Browse By

Topics

Departments

Centers, Labs, & Programs

Schools

Topic