Image recognition: Visual grouping, recognition, and learning

Vision extracts useful information from images. Reconstructing the three-dimensional structure of our environment and recognizing the objects that populate it are among the most important functions of our visual system. Computer vision researchers study the computational principles of vision and aim at designing algorithms that reproduce these functions. Vision is difficult: the same scene may give rise to very different images depending on illumination and viewpoint. Typically, an astronomical number of hypotheses exist that in principle have to be analyzed to infer a correct scene description. Moreover, image information might be extracted at different levels of spatial and logical resolution dependent on the image processing task. Knowledge of the world allows the visual system to limit the amount of ambiguity and to greatly simplify visual computations. We discuss how simple properties of the world are captured by the Gestalt rules of grouping, how the visual system may learn and organize models of objects for recognition, and how one may control the complexity of the description that the visual system computes.

Reactivation of encoding-related brain activity during memory retrieval

Neuronal models predict that retrieval of specific event information reactivates brain regions that were active during encoding of this information. Consistent with this prediction, this positron-emission tomography study showed that remembering that visual words had been paired with sounds at encoding activated some of the auditory brain regions that were engaged during encoding. After word-sound encoding, activation of auditory brain regions was also observed during visual word recognition when there was no demand to retrieve auditory information. Collectively, these observations suggest that information about the auditory components of multisensory event information is stored in auditory responsive cortex and reactivated at retrieval, in keeping with classical ideas about “redintegration,” that is, the power of part of an encoded stimulus complex to evoke the whole experience.

Temporal dynamics of verbal object comprehension

Knowledge of the stage composition and the temporal dynamics of human cognitive operations is critical for building theories of higher mental activity. This information has been difficult to acquire, even with different combinations of techniques such as refined behavioral testing, electrical recording/interference, and metabolic imaging studies. Verbal object comprehension was studied herein in a single individual, by using three tasks (object naming, auditory word comprehension, and visual word comprehension), two languages (English and Farsi), and four techniques (stimulus manipulation, direct cortical electrical interference, electrocorticography, and a variation of the technique of direct cortical electrical interference to produce time-delimited effects, called timeslicing), in a subject in whom indwelling subdural electrode arrays had been placed for clinical purposes. Electrical interference at a pair of electrodes on the left lateral occipitotemporal gyrus interfered with naming in both languages and with comprehension in the language tested (English). The naming and comprehension deficit resulted from interference with processing of verbal object meaning. Electrocorticography indices of cortical activation at this site during naming started 250–300 msec after visual stimulus presentation. By using the timeslicing technique, which varies the onset of electrical interference relative to the behavioral task, we found that completion of processing for verbal object meaning varied from 450 to 750 msec after current onset. This variability was found to be a function of the subject’s familiarity with the objects.

Effects of muscarinic blockade in perirhinal cortex during visual recognition

Stimulus recognition in monkeys is severely impaired by destruction or dysfunction of the perirhinal cortex and also by systemic administration of the cholinergic-muscarinic receptor blocker, scopolamine. These two effects are shown here to be linked: Stimulus recognition was found to be significantly impaired after bilateral microinjection of scopolamine directly into the perirhinal cortex, but not after equivalent injections into the laterally adjacent visual area TE or into the dentate gyrus of the overlying hippocampal formation. The results suggest that the formation of stimulus memories depends critically on cholinergic-muscarinic activation of the perirhinal area, providing a new clue to how stimulus representations are stored.

Positron-emission tomography imaging of long-term shape recognition challenges

Long-term visual memory performance was impaired by two types of challenges: a diazepam challenge on acquisition and a sensory challenge on recognition. Using positron-emission tomography regional cerebral blood flow imaging, we studied the effect of these challenges on regional brain activation during the delayed recognition of abstract visual shapes as compared with a baseline fixation task. Both challenges induced a significant decrease in differential activation in the left fusiform gyrus, suggesting that this region is involved in the automatic or volitional comparison of incoming and stored stimuli. In contrast, thalamic differential activation increased in response to memory challenges. This increase might reflect enhanced retrieval attempts as a compensatory mechanism for restoring recognition performance.

Brain wave recognition of words

Electrical and magnetic brain waves of seven subjects under three experimental conditions were recorded for the purpose of recognizing which one of seven words was processed. The analysis consisted of averaging over trials to create prototypes and test samples, to both of which Fourier transforms were applied, followed by filtering and an inverse transformation to the time domain. The filters used were optimal predictive filters, selected for each subject and condition. Recognition rates, based on a least-squares criterion, varied widely, but all but one of 24 were significantly different from chance. The two best were above 90%. These results show that brain waves carry substantial information about the word being processed under experimental conditions of conscious awareness.

Visual constraints in foraging bumblebees: Flower size and color affect search time and flight behavior

In optimal foraging theory, search time is a key variable defining the value of a prey type. But the sensory-perceptual processes that constrain the search for food have rarely been considered. Here we evaluate the flight behavior of bumblebees (Bombus terrestris) searching for artificial flowers of various sizes and colors. When flowers were large, search times correlated well with the color contrast of the targets with their green foliage-type background, as predicted by a model of color opponent coding using inputs from the bees' UV, blue, and green receptors. Targets that made poor color contrast with their backdrop, such as white, UV-reflecting ones, or red flowers, took longest to detect, even though brightness contrast with the background was pronounced. When searching for small targets, bees changed their strategy in several ways. They flew significantly slower and closer to the ground, so increasing the minimum detectable area subtended by an object on the ground. In addition, they used a different neuronal channel for flower detection. Instead of color contrast, they used only the green receptor signal for detection. We relate these findings to temporal and spatial limitations of different neuronal channels involved in stimulus detection and recognition. Thus, foraging speed may not be limited only by factors such as prey density, flight energetics, and scramble competition. Our results show that understanding the behavioral ecology of foraging can substantially gain from knowledge about mechanisms of visual information processing.

Visual habit formation in monkeys with neurotoxic lesions of the ventrocaudal neostriatum

Visual habit formation in monkeys, assessed by concurrent visual discrimination learning with 24-h intertrial intervals (ITI), was found earlier to be impaired by removal of the inferior temporal visual area (TE) but not by removal of either the medial temporal lobe or inferior prefrontal convexity, two of TE's major projection targets. To assess the role in this form of learning of another pair of structures to which TE projects, namely the rostral portion of the tail of the caudate nucleus and the overlying ventrocaudal putamen, we injected a neurotoxin into this neostriatal region of several monkeys and tested them on the 24-h ITI task as well as on a test of visual recognition memory. Compared with unoperated monkeys, the experimental animals were unaffected on the recognition test but showed an impairment on the 24-h ITI task that was highly correlated with the extent of their neostriatal damage. The findings suggest that TE and its projection areas in the ventrocaudal neostriatum form part of a circuit that selectively mediates visual habit formation.

The neural development and organization of letter recognition: Evidence from functional neuroimaging, computational modeling, and behavioral studies

Although much of the brain’s functional organization is genetically predetermined, it appears that some noninnate functions can come to depend on dedicated and segregated neural tissue. In this paper, we describe a series of experiments that have investigated the neural development and organization of one such noninnate function: letter recognition. Functional neuroimaging demonstrates that letter and digit recognition depend on different neural substrates in some literate adults. How could the processing of two stimulus categories that are distinguished solely by cultural conventions become segregated in the brain? One possibility is that correlation-based learning in the brain leads to a spatial organization in cortex that reflects the temporal and spatial clustering of letters with letters in the environment. Simulations confirm that environmental co-occurrence does indeed lead to spatial localization in a neural network that uses correlation-based learning. Furthermore, behavioral studies confirm one critical prediction of this co-occurrence hypothesis, namely, that subjects exposed to a visual environment in which letters and digits occur together rather than separately (postal workers who process letters and digits together in Canadian postal codes) do indeed show less behavioral evidence for segregated letter and digit processing.

Lightness constancy in primary visual cortex

When the illumination of a visual scene changes, the quantity of light reflected from objects is altered. Despite this, the perceived lightness of the objects generally remains constant. This perceptual lightness constancy is thought to be important behaviorally for object recognition. Here we show that interactions from outside the classical receptive fields of neurons in primary visual cortex modulate neural responses in a way that makes them immune to changes in illumination, as is perception. This finding is consistent with the hypothesis that the responses of neurons in primary visual cortex carry information about surface lightness in addition to information about form. It also suggests that lightness constancy, which is sometimes thought to involve “higher-level” processes, is manifest at the first stage of visual cortical processing.

State of the art in continuous speech recognition.

In the past decade, tremendous advances in the state of the art of automatic speech recognition by machine have taken place. A reduction in the word error rate by more than a factor of 5 and an increase in recognition speeds by several orders of magnitude (brought about by a combination of faster recognition search algorithms and more powerful computers), have combined to make high-accuracy, speaker-independent, continuous speech recognition for large vocabularies possible in real time, on off-the-shelf workstations, without the aid of special hardware. These advances promise to make speech recognition technology readily available to the general public. This paper focuses on the speech recognition advances made through better speech modeling techniques, chiefly through more accurate mathematical modeling of speech sounds.

Training and search methods for speech recognition.

Speech recognition involves three processes: extraction of acoustic indices from the speech signal, estimation of the probability that the observed index string was caused by a hypothesized utterance segment, and determination of the recognized utterance via a search among hypothesized alternatives. This paper is not concerned with the first process. Estimation of the probability of an index string involves a model of index production by any given utterance segment (e.g., a word). Hidden Markov models (HMMs) are used for this purpose [Makhoul, J. & Schwartz, R. (1995) Proc. Natl. Acad. Sci. USA 92, 9956-9963]. Their parameters are state transition probabilities and output probability distributions associated with the transitions. The Baum algorithm that obtains the values of these parameters from speech data via their successive reestimation will be described in this paper. The recognizer wishes to find the most probable utterance that could have caused the observed acoustic index string. That probability is the product of two factors: the probability that the utterance will produce the string and the probability that the speaker will wish to produce the utterance (the language model probability). Even if the vocabulary size is moderate, it is impossible to search for the utterance exhaustively. One practical algorithm is described [Viterbi, A. J. (1967) IEEE Trans. Inf. Theory IT-13, 260-267] that, given the index string, has a high likelihood of finding the most probable utterance.